© 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. 70870
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    \
    -2.05
    釤
    -2.00
    因为
    -1.70
    at
    -1.66
     Anordnung
    -1.61
    ons
    -1.60
    ta
    -1.59
    ⃣
    -1.53
     Meldung
    -1.52
     Teilnahme
    -1.51
    POSITIVE LOGITS
    庒
    1.77
    是想
    1.72
    沨
    1.70
    ༀ
    1.70
    Crédit
    1.70
    唞
    1.70
    我这
    1.69
    ڧ
    1.68
    说不定
    1.63
    ཋ
    1.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.