© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36257
    Prev
    Next
    INDEX
    Explanations

    fill in the blanks

    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_40_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
    ਦੇ
    0.47
    ﹔
    0.44
    此时
    0.44
    %。
    0.43
    地に
    0.41
    ਰਾ
    0.39
    ᠢ
    0.38
    കര
    0.38
     ডায়
    0.38
    MILLISE
    0.37
    POSITIVE LOGITS
     of
    0.53
     to
    0.47
     essay
    0.40
     than
    0.38
    wide
    0.38
     viagra
    0.37
    achusetts
    0.37
     engagement
    0.36
     assessing
    0.36
    kup
    0.36
    Activations Density 0.002%

    No Known Activations