© 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. 10-GEMMASCOPE-RES-131K
    7. 128624
    Prev
    Next
    INDEX
    Explanations

    product codes and company names

    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
    ningen
    -1.46
     tenden
    -1.46
     kablo
    -1.42
    Примеча
    -1.40
     maks
    -1.39
    ths
    -1.38
     
    -1.36
     stund
    -1.35
     talle
    -1.35
    our
    -1.35
    POSITIVE LOGITS
     einwand
    1.41
    struzioni
    1.39
    iddhar
    1.38
    ğinde
    1.36
    lyser
    1.34
     ندار
    1.32
    yym
    1.31
     akzeptieren
    1.30
     verwijzen
    1.29
     described
    1.28
    Activations Density 0.016%

    No Known Activations