© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82527
    Prev
    Next
    INDEX
    Explanations

    code syntax and english text

    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
    zorg
    -0.76
     Entsch
    -0.72
    يدي
    -0.69
    fels
    -0.69
     spectral
    -0.69
     trình
    -0.68
     cysteine
    -0.68
     زدن
    -0.66
     traum
    -0.66
    gravity
    -0.65
    POSITIVE LOGITS
     weaving
    0.72
    ดด
    0.71
    parser
    0.70
    osome
    0.69
     fopen
    0.68
     Schreiben
    0.65
    MEAS
    0.64
     Kleidung
    0.64
     nip
    0.64
    Iw
    0.63
    Activations Density 0.190%

    No Known Activations