© 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. 109570
    Prev
    Next
    INDEX
    Explanations

    circuit court rules

    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
     glitter
    -0.67
    Portuguese
    -0.66
    Timers
    -0.65
    ingan
    -0.65
    diya
    -0.65
    距
    -0.65
     interruption
    -0.64
    αλ
    -0.64
    wnd
    -0.63
     performers
    -0.61
    POSITIVE LOGITS
    讐
    0.83
    rvats
    0.79
    ಷ್
    0.78
     SPIE
    0.77
    tenths
    0.75
    ો
    0.75
    投手
    0.73
     Parla
    0.72
    نیم
    0.71
     عاما
    0.71
    Activations Density 0.046%

    No Known Activations