© 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. 164052
    Prev
    Next
    INDEX
    Explanations

    information and specific words

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

    potential, resolution, rising

    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
    ani
    0.50
     물
    0.47
    semi
    0.47
     먹
    0.47
    ANG
    0.45
     یا
    0.45
    tes
    0.45
     অথবা
    0.45
     ;
    0.44
    typically
    0.44
    POSITIVE LOGITS
    чики
    0.51
    ೂರ್ವ
    0.46
     डिलिव
    0.46
     لوبوي
    0.46
    يزة
    0.45
    爣
    0.45
    мії
    0.45
     GIFT
    0.45
    મિંગ
    0.44
    все
    0.44
    Activations Density 0.001%

    No Known Activations