© 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. 45473
    Prev
    Next
    INDEX
    Explanations

    scrolling ticker

    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
    ceto
    -0.76
    PLICIT
    -0.75
     CARD
    -0.72
    UNO
    -0.71
     Fingerprint
    -0.70
    rounding
    -0.69
    UIControlState
    -0.69
    getExtras
    -0.69
     怪
    -0.69
    bende
    -0.68
    POSITIVE LOGITS
     ticker
    2.67
     marquee
    2.59
     scrolling
    2.34
    ticker
    2.14
     scroll
    1.85
    Ticker
    1.84
     marque
    1.80
     tick
    1.80
    mar
    1.77
     Mar
    1.69
    Activations Density 0.046%

    No Known Activations