© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 893
    Prev
    Next
    INDEX
    Explanations

    characters input

    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
     iglesia
    -1.90
     отдых
    -1.84
     merciless
    -1.78
     bellissimo
    -1.78
    它
    -1.75
     decisione
    -1.73
     dikirim
    -1.69
    鶫
    -1.69
     дела
    -1.68
    </sup>
    -1.67
    POSITIVE LOGITS
    '
    2.34
    })));
    1.96
     \
    1.95
     Однако
    1.94
     Він
    1.73
     the
    1.71
    );
    1.70
    谞
    1.66
    щет
    1.65
    力气
    1.59
    Activations Density 0.026%

    No Known Activations