© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110645
    Prev
    Next
    INDEX
    Explanations

    PV, DV, BV abbreviations

    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
     наличие
    -0.82
    ITIONAL
    -0.81
    ksjoner
    -0.78
     Chowdhury
    -0.77
     швидко
    -0.73
     łatwo
    -0.71
    对其
    -0.70
    SEGUIR
    -0.70
     geprüft
    -0.70
     پای
    -0.70
    POSITIVE LOGITS
     BV
    0.77
    шается
    0.73
     bestellen
    0.73
     megh
    0.71
     پلیس
    0.71
    zesse
    0.70
     Harcourt
    0.67
     startTime
    0.67
    pv
    0.67
     Blackstone
    0.66
    Activations Density 0.036%

    No Known Activations