© 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. 41114
    Prev
    Next
    INDEX
    Explanations

    at the

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

    browsers offer recommendations

    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
     케
    0.51
     кир
    0.51
     бое
    0.51
     сыгра
    0.48
     $((
    0.46
     giocatore
    0.45
     பாதிக்க
    0.45
     Ай
    0.45
     যাঁ
    0.45
     jedną
    0.45
    POSITIVE LOGITS
    k
    0.46
    ى
    0.46
    0.46
    nb
    0.45
    a
    0.45
     amazingly
    0.44
    ومات
    0.44
    作者
    0.44
    nx
    0.44
     roots
    0.43
    Activations Density 0.000%

    No Known Activations