© 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. 34258
    Prev
    Next
    INDEX
    Explanations

    string type declarations

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

    The neuron fires on instances of the token “string” (i.e. type annotations or type names “string” 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
     that
    -1.84
     this
    -1.51
     or
    -1.44
     it
    -1.35
     have
    -1.30
     If
    -1.23
     your
    -1.15
     everything
    -1.15
     all
    -1.14
     while
    -1.14
    POSITIVE LOGITS
    蹿
    1.13
    もあって
    1.12
     promis
    1.09
     frère
    1.09
    浮か
    1.06
    落ちて
    1.05
     Longitud
    1.05
    ということです
    1.05
     compatri
    1.04
     Recuper
    1.04
    Activations Density 0.002%

    No Known Activations