© 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. 31-GEMMASCOPE-2-RES-262K
    7. 37893
    Prev
    Next
    INDEX
    Explanations

    hypothetical AI doesn't exist yet

    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_31_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
     угле
    0.54
    ０
    0.52
    ༔
    0.51
     Христос
    0.50
     зе
    0.48
     ше
    0.47
    ولا
    0.47
     оса
    0.47
     importantes
    0.46
    د
    0.46
    POSITIVE LOGITS
     i
    0.52
     precis
    0.48
    ier
    0.48
    mun
    0.47
    ”.
    0.46
     w
    0.45
     numer
    0.45
     su
    0.45
    の設定
    0.44
     -
    0.44
    Activations Density 0.001%

    No Known Activations