© 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. 100206
    Prev
    Next
    INDEX
    Explanations

    truck types and uses

    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
    ཫ
    -2.83
    苼
    -2.70
    ↵
    -2.67
    7
    -2.59
    ：“
    -2.59
    “
    -2.58
    轳
    -2.56
    TryDecode
    -2.45
    1
    -2.39
    6
    -2.38
    POSITIVE LOGITS
     These
    2.81
    𓋼
    2.47
    ☎️
    2.42
    📞
    2.41
    ;
    2.38
    ₂)
    2.33
    蔼
    2.33
    蕷
    2.31
    .,
    2.30
    鉭
    2.30
    Activations Density 0.007%

    No Known Activations