© 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. 89963
    Prev
    Next
    INDEX
    Explanations

    unicode runes

    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
    ayak
    -0.82
    創業
    -0.80
     đuôi
    -0.73
     PLWABN
    -0.73
     cercle
    -0.68
    тельного
    -0.67
    gazione
    -0.67
     colli
    -0.66
    round
    -0.66
    TIM
    -0.65
    POSITIVE LOGITS
     rune
    2.08
     runes
    1.77
     Rune
    1.48
    rune
    1.48
    Rune
    1.41
     byte
    1.13
     run
    1.12
    Run
    1.07
     Run
    1.03
     RUN
    1.03
    Activations Density 0.156%

    No Known Activations