© 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. 8447
    Prev
    Next
    INDEX
    Explanations

    do better than

    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
    そも
    -1.45
     attaque
    -1.40
     gracioso
    -1.38
    事も
    -1.38
    靺
    -1.37
     dekoratif
    -1.36
    どれだけ
    -1.36
     rígida
    -1.36
     físico
    -1.34
    誰か
    -1.34
    POSITIVE LOGITS
    這
    1.69
    这
    1.54
     than
    1.52
     and
    1.41
    <td>
    1.32
    所有
    1.30
    紅茶
    1.30
    He
    1.27
     antiche
    1.27
    This
    1.23
    Activations Density 0.019%

    No Known Activations