© 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. 87180
    Prev
    Next
    INDEX
    Explanations

    unicode character names

    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
    ressive
    -0.73
     enclosed
    -0.71
    Осно
    -0.70
    umab
    -0.69
     strtok
    -0.68
     தே
    -0.67
    Css
    -0.66
     economic
    -0.66
    EDIA
    -0.66
     or
    -0.65
    POSITIVE LOGITS
     listado
    0.79
     elles
    0.79
    )<<
    0.78
    )>>
    0.78
    лась
    0.78
     川
    0.77
     músicos
    0.77
     TREATMENT
    0.77
    qian
    0.76
     italianos
    0.76
    Activations Density 0.037%

    No Known Activations