© 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. 22-GEMMASCOPE-RES-131K
    7. 28573
    Prev
    Next
    INDEX
    Explanations

    function call arguments and return values

    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
     Προ
    -1.09
     you
    -1.02
     You
    -0.97
    Răsp
    -0.97
     If
    -0.96
     Ό
    -0.94
     Are
    -0.94
    Προ
    -0.94
    }$,
    -0.94
     with
    -0.93
    POSITIVE LOGITS
    前言
    1.03
     Federación
    1.02
     Grüsse
    0.96
     zakoń
    0.95
    Ответить
    0.94
     combinatie
    0.93
    ǽ
    0.92
     étage
    0.91
    //(
    0.90
    //*/
    0.90
    Activations Density 0.029%

    No Known Activations