© 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. 102697
    Prev
    Next
    INDEX
    Explanations

    Predaking, Gold/Silver, WHO principles, Roy Finch

    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
     cabinets
    -0.75
    ingos
    -0.74
    blo
    -0.72
    謄
    -0.72
    etype
    -0.72
     USG
    -0.71
     Overture
    -0.71
    やか
    -0.69
     matur
    -0.68
    blocks
    -0.68
    POSITIVE LOGITS
     Pred
    0.87
    Pred
    0.75
    ::_
    0.69
    fashionable
    0.69
     Clerical
    0.69
     jaar
    0.68
    qrcode
    0.68
     pred
    0.68
    annels
    0.68
     tối
    0.66
    Activations Density 0.017%

    No Known Activations