© 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. 10-GEMMASCOPE-RES-131K
    4. 105467
    Prev
    Next
    INDEX
    Explanations

    their relationship or subsequent item

    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
     only
    -1.51
     if
    -1.48
     even
    -1.29
    []=$
    -1.19
    </blockquote>
    -1.19
    "}}>
    -1.16
     where
    -1.14
    </td>
    -1.14
    "));
    -1.12
     If
    -1.11
    POSITIVE LOGITS
     are
    1.94
     respective
    1.80
    respectively
    1.45
     respectively
    1.45
    respective
    1.30
    ごめん
    1.16
     Feinde
    1.14
     then
    1.11
    easily
    1.11
     kré
    1.09
    Activations Density 0.367%

    No Known Activations