© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45030
    Prev
    Next
    INDEX
    Explanations

    list sequences of numbers or booleans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    1.01
    ing
    0.95
    :
    0.91
     de
    0.88
    are
    0.72
    га
    0.71
    or
    0.67
    ,
    0.67
     or
    0.67
    el
    0.66
    POSITIVE LOGITS
     可能
    0.67
     Pokud
    0.66
     използ
    0.64
     判断
    0.61
     patip
    0.61
     Entonces
    0.60
    quele
    0.59
    ための
    0.58
    ️⃣
    0.58
     並
    0.58
    Activations Density 0.026%

    No Known Activations