© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36500
    Prev
    Next
    INDEX
    Explanations

    Button, medal, OK, Five, Credit, Per, What

    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
     chronique
    -0.97
     demonio
    -0.96
     expliqué
    -0.95
     torne
    -0.91
     kena
    -0.91
    匾
    -0.90
    termilk
    -0.89
    usura
    -0.89
     Mindest
    -0.88
     africano
    -0.88
    POSITIVE LOGITS
     to
    0.82
     elsewhere
    0.80
     on
    0.79
    úsqueda
    0.78
    ständig
    0.75
     will
    0.75
     insufficiency
    0.73
     sovereigns
    0.72
     actually
    0.72
     from
    0.72
    Activations Density 0.000%

    No Known Activations