© 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. 82249
    Prev
    Next
    INDEX
    Explanations

    attribution, trib, contrib, distribu

    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
     Miao
    -0.87
     restring
    -0.79
     Contracts
    -0.77
    vég
    -0.76
     շ
    -0.75
    えもん
    -0.75
     Biele
    -0.74
     atoms
    -0.73
    Audi
    -0.72
     صورتی
    -0.71
    POSITIVE LOGITS
    ubu
    0.91
     band
    0.91
     نحو
    0.83
     bands
    0.82
     paid
    0.81
    band
    0.80
    UTE
    0.80
    ulink
    0.77
    จัด
    0.77
     izvē
    0.76
    Activations Density 0.033%

    No Known Activations