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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26625
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

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

    The neuron detects big comment‐block headers or banner‐style separators (e.g. lines of “*” or all-caps section titles) in source code.

    oai_token-act-pair · o4-miniTriggered 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
    ksamkeit
    -1.16
     continued
    -1.03
    CharStream
    -1.02
    iligung
    -0.98
     remaining
    -0.95
    เพื่อน
    -0.94
    𝒏
    -0.94
     continue
    -0.94
    んでいる
    -0.92
     through
    -0.89
    POSITIVE LOGITS
     definitions
    1.16
    在哪里
    1.08
     воду
    0.99
    釁
    0.99
     miſ
    0.98
     altitudes
    0.98
     astu
    0.98
     شروع
    0.98
    cifix
    0.96
    始める
    0.96
    Activations Density 0.097%

    No Known Activations