© 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. 40-GEMMASCOPE-2-RES-262K
    7. 212807
    Prev
    Next
    INDEX
    Explanations

    sql reader code

    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
     эта
    0.41
    Sprintf
    0.37
     रिलेटेड
    0.37
     وضعیت
    0.37
    ဏ်
    0.36
    iquant
    0.36
    ;$
    0.36
     Jumlah
    0.36
     compt
    0.35
    最大
    0.35
    POSITIVE LOGITS
    城镇
    0.45
     deacetyl
    0.38
     brin
    0.38
     countryside
    0.38
     abide
    0.38
    各自
    0.38
    眥
    0.37
     lawn
    0.36
     уча
    0.36
     золото
    0.36
    Activations Density 0.000%

    No Known Activations