© 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. 91693
    Prev
    Next
    INDEX
    Explanations

    rights reserved

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

    voltage distribution to neighborhoods

    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
    ment
    0.47
    ments
    0.47
    ぴ
    0.45
    держи
    0.45
    ího
    0.45
     vents
    0.44
    رت
    0.44
    ми
    0.43
    ized
    0.43
    рав
    0.43
    POSITIVE LOGITS
     mapView
    0.57
     включают
    0.47
    agata
    0.47
     myogenic
    0.45
     Electrode
    0.44
    繫
    0.44
     Arth
    0.43
     Spawn
    0.42
     Evam
    0.42
     Hudson
    0.42
    Activations Density 0.000%

    No Known Activations