© 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. 83411
    Prev
    Next
    INDEX
    Explanations

    Nos. followed by case numbers

    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
    AAAAA
    -0.72
    粗
    -0.70
     faveur
    -0.70
    鳩
    -0.69
    typeparam
    -0.69
    ésie
    -0.68
     chaleur
    -0.67
     Sprache
    -0.67
    ligkeit
    -0.66
     FRIENDS
    -0.66
    POSITIVE LOGITS
    sdag
    0.74
    ☂
    0.71
     Cerv
    0.66
    IVIDUAL
    0.66
    δη
    0.66
     реб
    0.65
     acı
    0.65
    $",
    0.65
    Shorts
    0.64
    Office
    0.64
    Activations Density 0.036%

    No Known Activations