© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15933
    Prev
    Next
    INDEX
    Explanations

    fee or subscription cost

    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_22/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
     livelli
    -1.34
    thèse
    -1.12
     finances
    -1.09
     περισσότε
    -1.08
     other
    -1.06
     spesa
    -1.04
     available
    -1.03
     típica
    -1.02
     fattori
    -1.02
     traseira
    -1.00
    POSITIVE LOGITS
     each
    1.34
    each
    1.22
     každ
    1.16
    每
    1.15
    antenimiento
    1.14
    bedienung
    1.11
    forEach
    1.10
     for
    1.10
     EACH
    1.09
    reiches
    1.07
    Activations Density 0.017%

    No Known Activations