© 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. 73098
    Prev
    Next
    INDEX
    Explanations

    indicating improvement

    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
     by
    -2.05
    还不错
    -1.78
     for
    -1.77
    bảng
    -1.75
     as
    -1.75
    鸩
    -1.70
    phòng
    -1.70
     prachtig
    -1.69
    珝
    -1.66
    後記
    -1.59
    POSITIVE LOGITS
    」
    2.00
    [
    1.86
    </
    1.76
    });
    1.74
    www
    1.60
    ”.
    1.57
    ”
    1.50
    </i>
    1.48
     userService
    1.46
    じ
    1.44
    Activations Density 0.018%

    No Known Activations