© 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. 79509
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

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

    The neuron is triggered by occurrences of the substring “junit” (as in package or import declarations referring to JUnit).

    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
     другим
    -1.23
    unikasi
    -1.21
    HasAnnotation
    -1.14
    ㄐ
    -1.13
    iek
    -1.13
    tivamente
    -1.09
    ۜ
    -1.08
     THESIS
    -1.07
    ISupport
    -1.06
    ParameterLimits
    -1.05
    POSITIVE LOGITS
    “
    1.44
    which
    1.44
    ’
    1.39
    .
    1.32
    ]
    1.25
    as
    1.23
    {
    1.23
    and
    1.15
    ＋
    1.13
    ><
    1.13
    Activations Density 0.000%

    No Known Activations