© 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. 129303
    Prev
    Next
    INDEX
    Explanations

    This neuron spots references to application model names or fixtures (e.g. identifiers in “models/... ” paths and fixture lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    class definitions and variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     frequentemente
    -1.20
    눙
    -1.19
     certamente
    -1.19
     WIL
    -1.17
    gorithm
    -1.16
    olingo
    -1.15
     symboles
    -1.13
     adota
    -1.13
     générer
    -1.13
     tornillos
    -1.13
    POSITIVE LOGITS
     after
    1.38
     still
    1.20
     or
    1.12
     at
    1.09
     with
    1.09
     in
    1.05
     as
    1.05
     but
    0.99
     sehr
    0.98
     Providing
    0.98
    Activations Density 0.021%

    No Known Activations