© 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. 90910
    Prev
    Next
    INDEX
    Explanations

    binary forms, open label, first principles

    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
    RIS
    -0.77
     informações
    -0.76
     информа
    -0.75
    ZG
    -0.73
     RIS
    -0.73
     esterno
    -0.73
     WORKING
    -0.72
     movimiento
    -0.69
     Brewster
    -0.68
     自然
    -0.66
    POSITIVE LOGITS
     womb
    0.76
     Пор
    0.67
    ORN
    0.65
     Kore
    0.65
    涸
    0.63
    デビュー
    0.63
    gnano
    0.62
    tése
    0.62
    interpreter
    0.61
    gop
    0.60
    Activations Density 0.074%

    No Known Activations