© 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. 50435
    Prev
    Next
    INDEX
    Explanations

    license texts and code

    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
    落ち
    -0.77
    aminen
    -0.75
     migliorare
    -0.73
     tempore
    -0.73
    oidal
    -0.73
    太陽
    -0.71
    AppendLine
    -0.71
     APPROPRI
    -0.70
    digt
    -0.69
    isfile
    -0.69
    POSITIVE LOGITS
     even
    0.70
     possibly
    0.70
    덟
    0.69
     裕
    0.68
     fourth
    0.68
     more
    0.67
    batik
    0.66
    Forth
    0.65
     know
    0.64
     three
    0.64
    Activations Density 0.080%

    No Known Activations