© 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. 11355
    Prev
    Next
    INDEX
    Explanations

    agency, agent, efficacy, intention

    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
     we
    -1.87
    **/
    -1.34
     groen
    -1.25
     harte
    -1.24
     чтобы
    -1.23
    </strong>
    -1.22
     kuns
    -1.20
     lachen
    -1.19
     Werken
    -1.19
    mental
    -1.19
    POSITIVE LOGITS
     ciertamente
    1.41
     rád
    1.31
     ذلك
    1.30
     uiteindelijk
    1.25
     actualizaciones
    1.24
     rám
    1.22
     vervolgens
    1.20
    características
    1.20
    陡
    1.19
    idends
    1.17
    Activations Density 0.030%

    No Known Activations