© 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. 102407
    Prev
    Next
    INDEX
    Explanations

    free software / open source licenses

    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
     凉
    -0.78
    point
    -0.75
     Rud
    -0.71
     阿
    -0.70
     Pipeline
    -0.69
     Georgia
    -0.68
     Austin
    -0.68
    Pipeline
    -0.68
     Ballroom
    -0.66
    Ⓟ
    -0.66
    POSITIVE LOGITS
    ')]
    0.78
    ')}}
    0.76
     Wann
    0.70
     목
    0.69
    のみ
    0.68
    ()].
    0.68
     Helsinki
    0.68
    ជ
    0.66
    inco
    0.66
    に行って
    0.65
    Activations Density 0.070%

    No Known Activations