© 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. 74218
    Prev
    Next
    INDEX
    Explanations

    model

    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
    )$
    -1.73
     neuen
    -1.63
     aktuellen
    -1.50
    2
    -1.49
    ↵↵
    -1.48
     you
    -1.46
     including
    -1.41
     FOR
    -1.41
    ).
    -1.36
     Ajoutez
    -1.36
    POSITIVE LOGITS
     Þ
    1.70
     mesures
    1.68
     rôles
    1.55
     couver
    1.54
    erving
    1.54
     KON
    1.53
    甞
    1.50
     prises
    1.49
     cóc
    1.49
     filles
    1.48
    Activations Density 0.013%

    No Known Activations