© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41122
    Prev
    Next
    INDEX
    Explanations

    importance

    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
    躂
    -1.61
     weitgehend
    -1.59
    Teilen
    -1.56
     heuti
    -1.54
    </i>
    -1.54
     prová
    -1.46
    時間は
    -1.45
     choisissez
    -1.45
     человека
    -1.42
     dobře
    -1.40
    POSITIVE LOGITS
     since
    2.05
     then
    2.03
     they
    2.02
     in
    2.00
     their
    1.84
     for
    1.79
     that
    1.71
     there
    1.59
     to
    1.46
     of
    1.40
    Activations Density 0.029%

    No Known Activations