© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146259
    Prev
    Next
    INDEX
    Explanations

    SCAMPER and petticoats

    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_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
     LIVING
    0.71
    趙
    0.69
     Lazy
    0.68
     دادن
    0.68
    Living
    0.66
     Living
    0.65
     замо
    0.64
     холо
    0.63
     поддер
    0.63
    赵
    0.62
    POSITIVE LOGITS
     tương
    0.66
    gui
    0.66
     نها
    0.65
     renounce
    0.63
     bleue
    0.63
    Portale
    0.62
     restructure
    0.62
    ौसी
    0.62
     anniversaire
    0.60
     gui
    0.60
    Activations Density 0.001%

    No Known Activations