© 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. 25607
    Prev
    Next
    INDEX
    Explanations

    accented characters

    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
    owa
    -0.96
    ijs
    -0.78
    讷
    -0.78
    ')[
    -0.77
    Dienstag
    -0.75
    killing
    -0.74
    kaufs
    -0.74
     engagements
    -0.73
    CGRectMake
    -0.73
     look
    -0.73
    POSITIVE LOGITS
     września
    0.90
    lapsingToolbar
    0.83
    yk
    0.75
    czny
    0.74
    腺
    0.73
    לה
    0.71
    状態で
    0.71
     dựng
    0.70
    parsing
    0.70
    raš
    0.67
    Activations Density 0.005%

    No Known Activations