© 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. 62322
    Prev
    Next
    INDEX
    Explanations

    weekly web, our flash, where you, are fun

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

    modelbeam, wind, breeze, thread

    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
     perpendicularly
    0.49
     ecclesiastical
    0.49
     ե
    0.48
     ecl
    0.47
     частности
    0.47
     peculiarities
    0.46
     кни
    0.46
     эл
    0.46
    og
    0.46
    ogt
    0.46
    POSITIVE LOGITS
    Apache
    0.46
     viszont
    0.46
    Android
    0.43
    Anderson
    0.42
    ურთი
    0.42
    atek
    0.42
    عليه
    0.41
    玩
    0.41
    شار
    0.41
    الہ
    0.41
    Activations Density 0.001%

    No Known Activations