© 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. 65790
    Prev
    Next
    INDEX
    Explanations

    variable declarations and assignments

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

    The neuron fires on identifiers used as object or struct properties—i.e. names that appear immediately after a “.” or “->” (or similar) access operator in 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_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
     pomaga
    -1.08
    alamualaikum
    -0.95
    []={
    -0.94
     Biophys
    -0.94
     samoch
    -0.94
     segíts
    -0.93
    deas
    -0.91
     görünü
    -0.90
     biedt
    -0.90
     aquele
    -0.90
    POSITIVE LOGITS
     =
    2.14
     +=
    1.24
     |=
    1.07
    }}=
    1.04
     said
    1.03
    setattr
    1.03
     also
    0.99
     however
    0.98
    PropertyChanged
    0.97
    리는
    0.94
    Activations Density 0.010%

    No Known Activations