© 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. 45018
    Prev
    Next
    INDEX
    Explanations

    convention

    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
    埽
    -3.50
     или
    -2.94
    ⎚
    -2.83
    или
    -2.75
     یا
    -2.69
    genodigd
    -2.59
    หรือ
    -2.58
     atau
    -2.56
    或
    -2.55
    縢
    -2.52
    POSITIVE LOGITS
    ”,
    2.84
     After
    2.80
    ”:
    2.69
    It
    2.64
     cuidadosamente
    2.63
    ”;
    2.63
     oorsp
    2.63
    "])
    2.53
    );
    2.53
    </sup>
    2.48
    Activations Density 0.004%

    No Known Activations