© 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. 10892
    Prev
    Next
    INDEX
    Explanations

    file path separators

    np_acts-logits-general · gemini-2.5-flash-lite

    URLs or file paths containing hyphens or underscores, particularly in compound technical terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    5
    -2.02
    3
    -1.98
    6
    -1.95
    4
    -1.80
    2
    -1.78
    7
    -1.76
    9
    -1.69
    1
    -1.67
    还是很
    -1.59
    8
    -1.49
    POSITIVE LOGITS
     and
    1.93
     without
    1.73
     a
    1.72
     some
    1.70
     one
    1.68
     what
    1.68
     those
    1.66
     for
    1.59
     such
    1.53
     our
    1.52
    Activations Density 0.054%

    No Known Activations