© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40292
    Prev
    Next
    INDEX
    Explanations

    section headings and subsequent details

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects the “c” character (often with adjacent underscores) as used in C source‐file names or C code identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the character 'c' appearing immediately after an underscore in code or formatted text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    code-style C identifiers or filenames with heavy use of underscores and alphanumeric segments.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     they
    -1.19
    assertAll
    -1.18
     APPELL
    -1.16
     angusti
    -1.14
     только
    -1.12
     their
    -1.09
     Küste
    -1.08
    *~*~
    -1.03
    ḳ
    -1.02
     hini
    -1.00
    POSITIVE LOGITS
    currently
    1.27
    ܆
    1.26
     SEVEN
    1.19
    obviously
    1.17
    ilding
    1.12
    слі
    1.10
     REMEMBER
    1.09
    ppens
    1.09
     生命周期
    1.08
    relatively
    1.07
    Activations Density 0.000%

    No Known Activations