© 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. 129949
    Prev
    Next
    INDEX
    Explanations

    scythe or reap

    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
     apocalyptic
    -2.23
     rife
    -2.16
     pilla
    -2.14
    \
    -2.11
    .”.
    -2.02
     extortion
    -2.02
    有好
    -1.98
    嵴
    -1.98
    的眼神
    -1.98
     acta
    -1.98
    POSITIVE LOGITS
    鼍
    2.16
    餍
    2.14
    
    2.08
     brugt
    1.99
    耵
    1.98
     valgt
    1.98
    凩
    1.95
    镲
    1.93
    鱨
    1.91
    圌
    1.91
    Activations Density 0.010%

    No Known Activations