© 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. 89892
    Prev
    Next
    INDEX
    Explanations

    listing numbers and punctuation

    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
     quanh
    -0.72
     Hunter
    -0.69
    ecan
    -0.69
     ISS
    -0.68
    ---|---|
    -0.66
     Basket
    -0.66
    nob
    -0.65
     dlc
    -0.65
     cylind
    -0.64
    Matthias
    -0.64
    POSITIVE LOGITS
    仮面
    0.73
    ╳
    0.69
    AZIONE
    0.69
    Золо
    0.67
    cillos
    0.67
    戸
    0.66
     Edmonds
    0.65
    彼の
    0.64
     adat
    0.64
    imler
    0.64
    Activations Density 0.083%

    No Known Activations