© 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. 21400
    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
    salomon
    -1.16
    clude
    -1.09
    ᚔ
    -1.07
    
    -1.06
     grumpy
    -1.05
     merveilleux
    -1.05
     proteína
    -1.04
     jengibre
    -1.04
     prenant
    -1.02
    রণ
    -1.02
    POSITIVE LOGITS
     believes
    1.12
     now
    1.06
    or
    1.02
     first
    1.02
    just
    0.98
     or
    0.97
     came
    0.96
     one
    0.94
     people
    0.94
     sizeable
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.