© 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. 8430
    Prev
    Next
    INDEX
    Explanations

    ending or topping off

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵↵
    -1.70
    corpion
    -1.63
     protagonisti
    -1.61
    étranger
    -1.60
     from
    -1.52
    casm
    -1.52
     There
    -1.51
     femminile
    -1.50
     to
    -1.49
    
    -1.49
    POSITIVE LOGITS
    ’
    2.36
    O
    1.99
    ir
    1.95
     één
    1.84
    not
    1.78
    ant
    1.78
    d
    1.78
    いかがでしたか
    1.66
    and
    1.59
    蹩
    1.59
    Activations Density 0.002%

    No Known Activations