© 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. 84036
    Prev
    Next
    INDEX
    Explanations

    code and foreign words

    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
    Dah
    -0.71
    Honest
    -0.69
     Vereine
    -0.67
    uario
    -0.67
    ah
    -0.66
     益
    -0.65
    GIUM
    -0.65
    DATE
    -0.64
     flute
    -0.64
     barren
    -0.63
    POSITIVE LOGITS
    руб
    0.75
    (({
    0.74
    illah
    0.71
    packaging
    0.69
    upported
    0.68
    مك
    0.67
    ostro
    0.67
    svc
    0.65
     IMP
    0.63
    مم
    0.63
    Activations Density 0.059%

    No Known Activations