© 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. 34-GEMMASCOPE-RES-131K
    7. 83952
    Prev
    Next
    INDEX
    Explanations

    CWE classifications and source code paths

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

    This neuron fires on code‐style identifiers and metadata—especially file‐path or template tokens marked by underscores, slashes, colons, asterisks, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Ceará
    -0.88
    🕺
    -0.85
    ）-
    -0.85
    dhury
    -0.84
    :%.
    -0.83
     notar
    -0.83
     strives
    -0.82
    цията
    -0.82
    ọt
    -0.82
     like
    -0.82
    POSITIVE LOGITS
     experimenter
    1.23
    ᴋ
    1.02
     večer
    0.99
    transQ
    0.97
     atrak
    0.96
    Psychology
    0.93
     μας
    0.92
    pří
    0.90
     pozna
    0.89
     AMAZING
    0.88
    Activations Density 0.000%

    No Known Activations