© 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. 11973
    Prev
    Next
    INDEX
    Explanations

    job seeker

    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
    .”
    -2.59
    });
    -2.38
    }
    -2.31
    */
    -2.30
    acterísticas
    -2.28
    ”
    -2.22
    os
    -2.19
     decreto
    -2.19
    镚
    -2.17
    价格
    -2.16
    POSITIVE LOGITS
    翾
    2.66
    𞤢
    2.34
    geſ
    2.27
    izienz
    2.16
    詒
    2.09
    灩
    2.08
    ୪
    2.06
    罴
    2.05
     creciente
    2.05
     These
    2.03
    Activations Density 0.003%

    No Known Activations