© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    numbers followed by S.E

    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
     )
    -2.17
    」
    -2.14
    ！”
    -2.14
    了一
    -2.13
    ”;
    -2.11
    });
    -1.99
    期限
    -1.95
     =
    -1.93
    …”
    -1.91
    ）
    -1.91
    POSITIVE LOGITS
     ſte
    2.56
    \
    2.41
    嚒
    2.38
    
    2.28
    葑
    2.28
    鸸
    2.22
    یل
    2.20
     \
    2.17
    geſ
    2.14
    呿
    2.14
    Activations Density 0.022%

    No Known Activations