© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66328
    Prev
    Next
    INDEX
    Explanations

    McDonald, McDougald, McPartlin

    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
    醫院
    -0.83
    ulta
    -0.81
    Opts
    -0.78
    iterraneo
    -0.76
     Discard
    -0.75
    ép
    -0.74
     awhile
    -0.74
    roix
    -0.73
     dlou
    -0.72
     sometime
    -0.72
    POSITIVE LOGITS
    ETHODS
    0.81
    ések
    0.80
     важ
    0.73
     же
    0.73
     XNUMX
    0.70
     Desai
    0.68
     конца
    0.66
    riterion
    0.66
    addObject
    0.66
     начала
    0.66
    Activations Density 0.021%

    No Known Activations