© 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. 102816
    Prev
    Next
    INDEX
    Explanations

    up

    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
    ↵
    -3.03
    '
    -2.31
    
    -1.95
    "
    -1.69
    er
    -1.67
     outono
    -1.67
     réglementation
    -1.63
    ecause
    -1.59
     consentimento
    -1.58
     dernières
    -1.52
    POSITIVE LOGITS
    𖧵
    1.90
    沨
    1.88
    cinoma
    1.86
    toires
    1.83
    |$.
    1.81
    ";
    1.74
    ógicos
    1.66
     轻
    1.65
     HttpNotFound
    1.65
    𒊹
    1.64
    Activations Density 0.008%

    No Known Activations