© 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. 8054
    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
     their
    -1.33
    omega
    -1.28
     from
    -1.23
    end
    -1.21
    get
    -1.20
     dovr
    -1.19
    lling
    -1.15
    They
    -1.13
    々な
    -1.13
    но
    -1.12
    POSITIVE LOGITS
     banyo
    1.49
     ۱۸
    1.44
     таких
    1.44
     этих
    1.38
     Conferencia
    1.30
     maïs
    1.20
    ńst
    1.20
     presunto
    1.20
     ۶
    1.19
    垍
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.