© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21754
    Prev
    Next
    INDEX
    Explanations

    HTML container divs

    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
    gehende
    -1.81
    kadang
    -1.74
    ᗯ
    -1.74
    y
    -1.74
    鹮
    -1.73
    ganggu
    -1.72
     bemerk
    -1.71
     纹身
    -1.71
     entweder
    -1.70
     forskellige
    -1.69
    POSITIVE LOGITS
    \
    2.05
    ;"
    1.85
     Both
    1.84
     =
    1.82
    心中的
    1.80
    様な
    1.76
    姿を
    1.73
    復帰
    1.70
    。『
    1.67
     emple
    1.64
    Activations Density 0.003%

    No Known Activations