© 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. 143599
    Prev
    Next
    INDEX
    Explanations

    flesh and us

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

    probabilities, analysis, models

    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
    ڑ
    0.54
     بررسی
    0.51
    铨
    0.51
    ه‌های
    0.51
    лог
    0.50
    وٹ
    0.48
    ငံ
    0.47
     सबकी
    0.47
    و
    0.46
     Query
    0.45
    POSITIVE LOGITS
    Ordered
    0.53
    acio
    0.49
    olik
    0.48
    ，
    0.46
    '>
    0.45
    $)$.
    0.45
    cita
    0.43
     enfrenta
    0.43
     zakon
    0.43
    kei
    0.43
    Activations Density 0.001%

    No Known Activations