© 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. 34-GEMMASCOPE-RES-131K
    7. 63039
    Prev
    Next
    INDEX
    Explanations

    code definition syntax

    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_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
    umeur
    -0.87
    Nationalité
    -0.75
    时
    -0.75
    ormány
    -0.74
     from
    -0.74
    latable
    -0.73
    ïc
    -0.73
    торы
    -0.72
     rowspan
    -0.71
    Summer
    -0.70
    POSITIVE LOGITS
     todėl
    0.95
     cache
    0.94
     اظهار
    0.82
     Cache
    0.81
     caching
    0.78
     NINE
    0.77
     halos
    0.75
    diği
    0.75
     cached
    0.74
     pudding
    0.74
    Activations Density 0.003%

    No Known Activations