© 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. 72452
    Prev
    Next
    INDEX
    Explanations

    doi identifiers

    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
     to
    -2.36
     have
    -2.25
     That
    -2.08
     but
    -1.86
     on
    -1.75
     Many
    -1.74
     maybe
    -1.73
     Even
    -1.73
     being
    -1.67
     even
    -1.65
    POSITIVE LOGITS
     verborgen
    1.87
     kredi
    1.77
    ↑↑
    1.77
    OBJETIVO
    1.75
     hırka
    1.73
    鲥
    1.72
     手绘
    1.71
     geladen
    1.70
    ●●
    1.70
     seraient
    1.70
    Activations Density 0.001%

    No Known Activations