© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4818
    Prev
    Next
    INDEX
    Explanations

    rooms and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    蛄
    0.75
    注入
    0.65
    ipore
    0.65
    ણી
    0.65
     সর্বনাশ
    0.63
     dimens
    0.63
     done
    0.63
     równ
    0.63
     mieć
    0.62
    赛
    0.62
    POSITIVE LOGITS
     laundry
    0.93
    Laundry
    0.90
    Master
    0.83
     Master
    0.83
     Laundry
    0.81
    master
    0.80
    MASTER
    0.78
     master
    0.77
     Backyard
    0.75
     powder
    0.72
    Activations Density 0.016%

    No Known Activations