© 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. 113282
    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
    زيل
    -1.02
     Männern
    -1.00
     бампер
    -0.97
    עוד
    -0.94
     chestnuts
    -0.94
    それから
    -0.93
     evrops
    -0.93
     procurar
    -0.93
    isburg
    -0.93
     diferenças
    -0.91
    POSITIVE LOGITS
     Jugos
    0.99
     asthma
    0.98
    ORI
    0.98
     hatta
    0.98
    Bissau
    0.96
    )
    0.93
    titudes
    0.91
    ori
    0.91
     SEQUENCE
    0.91
     palladium
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.