© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2411
    Prev
    Next
    INDEX
    Explanations

    HPP files and characterization

    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
     already
    -0.82
    =",
    -0.77
    êtement
    -0.75
    ğini
    -0.72
    想像
    -0.72
    liptical
    -0.71
    ívne
    -0.71
     nito
    -0.71
    他是
    -0.71
     rowspan
    -0.71
    POSITIVE LOGITS
    有些不
    0.86
    ویژگی
    0.85
     hall
    0.84
    FieldNumber
    0.81
     feature
    0.81
    崖
    0.81
    達到
    0.81
    зя
    0.81
     ciągu
    0.81
     frage
    0.79
    Activations Density 0.000%

    No Known Activations