© 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. 34-GEMMASCOPE-RES-131K
    7. 30708
    Prev
    Next
    INDEX
    Explanations

    words followed by specific sequences

    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_34/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
     delightful
    -0.81
    routed
    -0.79
     หม
    -0.78
    エリー
    -0.76
     simplu
    -0.74
    没错
    -0.73
    EXCEPT
    -0.72
     lowly
    -0.72
    ETYPE
    -0.71
    unes
    -0.71
    POSITIVE LOGITS
    dispatcher
    0.82
    ovec
    0.79
    wwwwwwww
    0.77
     compacta
    0.77
     fax
    0.77
    setMax
    0.77
    🔥
    0.76
     Cleo
    0.76
    fusion
    0.75
    raeli
    0.74
    Activations Density 0.002%

    No Known Activations