© 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. 45530
    Prev
    Next
    INDEX
    Explanations

    citations, metadata, email headers

    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
     Bari
    -0.69
     otaku
    -0.68
    ップ
    -0.66
    DataField
    -0.66
     Jennings
    -0.65
    kiel
    -0.64
    >\<
    -0.64
    çu
    -0.64
    Fen
    -0.63
    kologie
    -0.63
    POSITIVE LOGITS
    ีน
    0.74
     altro
    0.72
     being
    0.66
    وني
    0.65
     riego
    0.65
    所有人
    0.64
    Evt
    0.63
    AndFlush
    0.63
     Sport
    0.61
    raska
    0.61
    Activations Density 0.066%

    No Known Activations