© 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. 34-GEMMASCOPE-RES-131K
    7. 65286
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    ไม่
    -0.82
     palavras
    -0.80
     embarrassed
    -0.78
    تش
    -0.77
    咸
    -0.76
     Gerhard
    -0.74
    janya
    -0.73
    ()));
    -0.73
    Compound
    -0.72
     guaranteed
    -0.71
    POSITIVE LOGITS
     unjustly
    0.80
     skis
    0.79
    少的
    0.76
    玩的
    0.73
    Hamlet
    0.73
     gesamte
    0.71
     depositions
    0.71
    ἑ
    0.70
    Haber
    0.70
    久了
    0.70
    Activations Density 0.270%

    No Known Activations