© 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. 44907
    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
    Genau
    -1.02
    atória
    -0.95
    Einfach
    -0.93
    Doch
    -0.91
     Kessel
    -0.91
    Dieser
    -0.90
     aber
    -0.90
     sencillas
    -0.90
    Keine
    -0.90
     چ
    -0.88
    POSITIVE LOGITS
    ctical
    0.94
    zyć
    0.91
     kühl
    0.90
     Gerä
    0.88
    HECK
    0.88
    ゴルフ
    0.87
    になってしまう
    0.87
    queen
    0.84
    setImageResource
    0.84
     unglaub
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.