© 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. 10-GEMMASCOPE-RES-131K
    7. 934
    Prev
    Next
    INDEX
    Explanations

    indices like i and j

    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_10/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
    1
    -1.97
    or
    -1.56
    ––
    -1.52
     have
    -1.45
     faktisk
    -1.38
     Frühl
    -1.38
    <i>
    -1.38
    res
    -1.34
     hauptsächlich
    -1.34
    <em>
    -1.31
    POSITIVE LOGITS
     of
    1.37
    ubblica
    1.36
    poptosis
    1.31
     dieser
    1.30
    MAXN
    1.29
    maxn
    1.28
    Sábado
    1.27
     diesem
    1.25
    philosophy
    1.24
     aktuelle
    1.23
    Activations Density 0.012%

    No Known Activations