© 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. 847
    Prev
    Next
    INDEX
    Explanations

    plot with subplots

    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
    Specifiche
    -0.81
    onds
    -0.78
    ешь
    -0.76
    dept
    -0.75
    agrave
    -0.74
    Lagos
    -0.74
    AMOS
    -0.73
     医療
    -0.72
    ticism
    -0.71
     stdClass
    -0.71
    POSITIVE LOGITS
     textAlign
    1.19
     style
    1.09
    soft
    0.98
    textAlign
    0.93
     soft
    0.86
     max
    0.83
     Soft
    0.80
     النساء
    0.78
    overflow
    0.76
    Affect
    0.75
    Activations Density 0.002%

    No Known Activations