© 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. 40835
    Prev
    Next
    INDEX
    Explanations

    Q: or specific phrases

    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
     but
    -1.53
    (
    -1.36
    ↵↵↵
    -1.32
    ↵↵
    -1.30
     rústica
    -1.30
     flotante
    -1.28
     emisiones
    -1.23
     funcionam
    -1.20
     especta
    -1.20
     maravill
    -1.20
    POSITIVE LOGITS
     for
    1.57
     as
    1.49
    inawa
    1.41
    resz
    1.38
     stessi
    1.30
    setString
    1.27
     μας
    1.22
     iniziare
    1.22
     appunt
    1.20
    zamos
    1.20
    Activations Density 0.098%

    No Known Activations