© 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. 65241
    Prev
    Next
    INDEX
    Explanations

    white cotton pinafore

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

    obsolete, negligence, calculations, changes

    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
    Т
    0.54
    스
    0.51
    我认为
    0.49
    诙
    0.49
    א
    0.48
    明顯
    0.47
    Ско
    0.47
    ম
    0.47
    㻁
    0.45
    关于
    0.45
    POSITIVE LOGITS
     abandonar
    0.52
     nakon
    0.50
     insisted
    0.50
     forgo
    0.48
     lasciare
    0.48
     tijekom
    0.48
     sadece
    0.47
     vybaven
    0.47
     pendekatan
    0.46
     doar
    0.46
    Activations Density 0.000%

    No Known Activations