© 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. 39843
    Prev
    Next
    INDEX
    Explanations

    Plymouth, Brest, Milford, Sligo

    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
    </strong>
    -3.22
     
    -2.77
    0
    -2.73
    9
    -2.70
    <em>
    -2.67
    He
    -2.67
    on
    -2.61
    <strong>
    -2.59
    ('
    -2.55
    D
    -2.53
    POSITIVE LOGITS
    tamaris
    2.77
    鳙
    2.61
     그는
    2.61
    ).”
    2.59
     personalizar
    2.55
     neuem
    2.47
     biela
    2.44
    雳
    2.44
    
    2.42
    晔
    2.36
    Activations Density 0.002%

    No Known Activations