© 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. 112544
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    </th>
    -2.91
    to
    -2.80
    \
    -2.58
    ";
    -2.50
    "
    -2.42
    ":
    -2.39
    {
    -2.38
    </u>
    -2.36
    </h1>
    -2.36
    </strong>
    -2.20
    POSITIVE LOGITS
    趼
    3.09
     bahwa
    2.91
    拮
    2.81
    蠃
    2.81
    磲
    2.78
    闼
    2.70
    </h2>
    2.70
     econô
    2.67
    姈
    2.64
    阄
    2.63
    Activations Density 0.074%

    No Known Activations