© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129272
    Prev
    Next
    INDEX
    Explanations

    sequence, Msgpack, BER, SGML

    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
     توسط
    -1.66
    又不
    -1.56
     recensioni
    -1.55
    ቼ
    -1.53
    又能
    -1.53
    ーん
    -1.51
     oleh
    -1.49
     한다
    -1.48
     サムネイル
    -1.46
    也知道
    -1.42
    POSITIVE LOGITS
    </strong>
    1.70
    <td>
    1.66
    约翰
    1.62
    '
    1.57
     año
    1.53
    .&
    1.47
     deben
    1.37
    怎样的
    1.35
    </em>
    1.33
    grö
    1.30
    Activations Density 0.005%

    No Known Activations