© 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. 83987
    Prev
    Next
    INDEX
    Explanations

    file names with `com` or numbers

    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
    arked
    -0.71
     vidare
    -0.70
     väx
    -0.70
     bookId
    -0.68
     Bronze
    -0.66
    ႆ
    -0.65
     HDMI
    -0.64
     kitabı
    -0.63
    ună
    -0.63
    균
    -0.63
    POSITIVE LOGITS
    וח
    0.75
     leb
    0.71
     fulness
    0.68
     Dmit
    0.68
    anson
    0.68
    Ос
    0.68
    diversity
    0.67
    Ḳ
    0.67
     EXTRA
    0.66
     liber
    0.66
    Activations Density 0.070%

    No Known Activations