© 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. 73669
    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
    ፨
    -2.59
     ſever
    -2.38
     Dinas
    -2.36
     momentous
    -2.27
    嘬
    -2.23
     picturesque
    -2.20
     rése
    -2.19
    )];
    -2.19
     ',
    -2.17
     colossal
    -2.17
    POSITIVE LOGITS
     can
    2.64
     took
    2.53
     remained
    2.33
     ostensibly
    2.33
     gets
    2.30
     enables
    2.30
     went
    2.28
     gives
    2.25
     will
    2.23
     When
    2.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.