© 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. 197
    Prev
    Next
    INDEX
    Explanations

    code blocks and their results

    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
     any
    -1.98
    romas
    -1.66
     when
    -1.56
    gencias
    -1.51
     Polícia
    -1.46
     just
    -1.44
    áver
    -1.36
     schaff
    -1.35
    Solución
    -1.32
     a
    -1.31
    POSITIVE LOGITS
     were
    1.53
    待って
    1.41
    OGLE
    1.34
     it
    1.33
    valget
    1.32
    čeno
    1.32
    How
    1.30
     spokoj
    1.30
    にとっては
    1.28
     クルー
    1.28
    Activations Density 0.004%

    No Known Activations