© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42971
    Prev
    Next
    INDEX
    Explanations

    Texas / moment / he

    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
    </sup>
    -2.00
    '
    -1.99
     &
    -1.99
     jį
    -1.91
     him
    -1.84
    </h4>
    -1.82
    0
    -1.79
    戗
    -1.77
    </h2>
    -1.71
     appartamento
    -1.70
    POSITIVE LOGITS
     стороне
    1.88
    This
    1.80
     However
    1.79
     Though
    1.79
    孭
    1.78
    ją
    1.68
    cedes
    1.68
     Despite
    1.64
    зопас
    1.63
     There
    1.62
    Activations Density 0.013%

    No Known Activations