© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5012
    Prev
    Next
    INDEX
    Explanations

    readable and workable 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_31_width_16k_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
    прода
    0.71
    𒉡
    0.64
    рующих
    0.57
    行う
    0.57
    판매
    0.56
    ing
    0.56
    ро
    0.55
     ventas
    0.55
    。
    0.55
    recursion
    0.54
    POSITIVE LOGITS
    যোগ্য
    0.77
    able
    0.71
    ABLE
    0.65
    izable
    0.63
     łat
    0.58
     workable
    0.57
     kW
    0.57
    க்கூடிய
    0.55
    ability
    0.51
    ง่าย
    0.51
    Activations Density 0.436%

    No Known Activations