© 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. 33451
    Prev
    Next
    INDEX
    Explanations

    code variables and identifiers

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

    The neuron fires on programming identifiers—variable, method, or constant names 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_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
     which
    -1.93
     this
    -1.52
     their
    -1.45
     for
    -1.34
     in
    -1.31
     by
    -1.30
     when
    -1.29
     они
    -1.28
     our
    -1.25
     of
    -1.20
    POSITIVE LOGITS
    extremely
    1.25
    垟
    1.15
    another
    1.15
    excellent
    1.13
    oluble
    1.13
    atique
    1.12
     consultato
    1.10
    potentially
    1.09
     flamboyant
    1.09
    damente
    1.08
    Activations Density 0.014%

    No Known Activations