© 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. 71666
    Prev
    Next
    INDEX
    Explanations

    constructor, import, state

    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
     from
    -0.95
     at
    -0.92
     sterben
    -0.86
     incríveis
    -0.84
    に来て
    -0.84
     and
    -0.83
     küm
    -0.83
     sienta
    -0.83
     possibilidades
    -0.82
    Ár
    -0.82
    POSITIVE LOGITS
    겠
    0.90
    witches
    0.89
     split
    0.87
     MD
    0.87
    inen
    0.85
     build
    0.85
     لم
    0.85
    袄
    0.84
    vrons
    0.84
     vincula
    0.83
    Activations Density 0.002%

    No Known Activations