© 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. 112583
    Prev
    Next
    INDEX
    Explanations

    surpassing expectations or competitors

    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
     betyr
    -2.56
    ";
    -2.47
    "))
    -2.38
    </h3>
    -2.36
    """
    -2.34
    "¿
    -2.31
    菝
    -2.25
     '
    -2.23
     betyder
    -2.23
    "
    -2.19
    POSITIVE LOGITS
    ↵
    2.67
    er
    2.64
    遢
    2.42
    他
    2.41
    …….
    2.41
    In
    2.39
    徙
    2.33
    ി
    2.31
     Fifteen
    2.31
    ');
    2.31
    Activations Density 0.002%

    No Known Activations