© 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. 91244
    Prev
    Next
    INDEX
    Explanations

    switch, updated, having satisfied

    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
    🏤
    -0.91
     Caleb
    -0.69
    leté
    -0.69
     verwij
    -0.68
    CEP
    -0.68
    tony
    -0.66
    missão
    -0.66
     WOLF
    -0.64
    ΐ
    -0.63
     Nef
    -0.61
    POSITIVE LOGITS
     familial
    0.72
    Zaj
    0.69
    Harry
    0.68
     broth
    0.66
    habi
    0.65
    ങ്ക
    0.65
    pstmt
    0.65
     update
    0.65
    突破
    0.64
    циях
    0.64
    Activations Density 0.058%

    No Known Activations