© 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. 75541
    Prev
    Next
    INDEX
    Explanations

    Rainbow Song, resonant control, ticket, effect

    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
     Coulomb
    -0.91
    jados
    -0.88
     pherom
    -0.86
     prawn
    -0.83
     silicate
    -0.82
     wineries
    -0.82
    Bung
    -0.80
     saluted
    -0.80
     tavern
    -0.79
     choirs
    -0.78
    POSITIVE LOGITS
    trab
    0.86
    lucky
    0.83
     deixe
    0.82
     aceit
    0.80
    centre
    0.77
     تحص
    0.77
     grátis
    0.77
    center
    0.76
    Už
    0.76
     Haskell
    0.75
    Activations Density 0.027%

    No Known Activations