© 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. 44193
    Prev
    Next
    INDEX
    Explanations

    places people and events

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

    ** emphasis or bolding

    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
    iter
    0.45
    amon
    0.45
    yuan
    0.43
    chym
    0.43
    剻
    0.43
    ki
    0.42
    h
    0.42
    ುಕ
    0.42
    nast
    0.42
    br
    0.41
    POSITIVE LOGITS
     خرا
    0.53
    ＃
    0.50
    ですし
    0.50
     недавно
    0.49
    Ƹ
    0.48
     সী
    0.48
     пля
    0.48
    ##
    0.47
     లక్ష
    0.47
     Часто
    0.47
    Activations Density 0.001%

    No Known Activations