© 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. 187464
    Prev
    Next
    INDEX
    Explanations

    interesting arrangements and ideas

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

    tooltips and descriptions

    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
    সম্যান
    0.48
     imprison
    0.48
     it
    0.48
     af
    0.46
     aeg
    0.44
     ef
    0.43
    涛
    0.43
    इड
    0.42
     eff
    0.42
     amid
    0.42
    POSITIVE LOGITS
    ORA
    0.50
    ан
    0.47
    oyo
    0.45
    вот
    0.45
    ам
    0.44
    чена
    0.44
    ahaan
    0.44
    ом
    0.44
    ой
    0.44
     घेतले
    0.44
    Activations Density 0.000%

    No Known Activations