© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219843
    Prev
    Next
    INDEX
    Explanations

    wiring diagrams and technical instruments

    np_acts-logits-general · gemini-2.5-flash-lite

    longass label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hungary
    0.55
    Ꮡ
    0.54
     швидко
    0.53
     น้อย
    0.53
     ۷
    0.52
    рин
    0.52
     що
    0.51
     самостоя
    0.50
     ውሃ
    0.50
     ਰ
    0.50
    POSITIVE LOGITS
     rows
    0.48
     ROWS
    0.47
    ↵
    0.43
     projects
    0.42
     sections
    0.42
     productions
    0.42
     riffs
    0.42
     WIRE
    0.41
     translates
    0.40
     November
    0.40
    Activations Density 0.000%

    No Known Activations