© 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. 38140
    Prev
    Next
    INDEX
    Explanations

    state government and locations

    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
     descrito
    -0.70
    benzo
    -0.67
    ūrė
    -0.67
    ฉ
    -0.66
     Carrot
    -0.66
    。<
    -0.65
     direc
    -0.65
    POD
    -0.64
    Durability
    -0.64
     colspan
    -0.63
    POSITIVE LOGITS
     Accu
    0.78
     قلم
    0.73
     rhythmic
    0.73
     Projekte
    0.71
     অন
    0.68
     bacteria
    0.67
    INTERNAL
    0.66
    WIDTH
    0.66
    arbe
    0.66
    ड़ा
    0.65
    Activations Density 0.069%

    No Known Activations