© 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. 84294
    Prev
    Next
    INDEX
    Explanations

    developed with, might signal, start from

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

    rice paddies and Snowflake Data

    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
     afternoons
    0.49
    א
    0.48
     ਅ
    0.47
    ポイント
    0.46
    ارهای
    0.46
    ittäin
    0.45
    അ
    0.45
    नाडा
    0.44
    ക്
    0.44
    แต
    0.44
    POSITIVE LOGITS
     potted
    0.52
     Democr
    0.49
     Communications
    0.47
     solidly
    0.46
     Many
    0.46
     planted
    0.46
    顗
    0.45
     Document
    0.45
     decidedly
    0.44
     如
    0.44
    Activations Density 0.001%

    No Known Activations