© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148224
    Prev
    Next
    INDEX
    Explanations

    Studio followed by ai or G

    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
    Corona
    0.65
     весь
    0.62
     Corona
    0.62
    policies
    0.61
    国务院
    0.60
    人民
    0.59
     api
    0.59
    ="__
    0.59
    Zoom
    0.58
     sech
    0.58
    POSITIVE LOGITS
    halter
    0.85
     caste
    0.76
    otipo
    0.75
     hind
    0.75
     партне
    0.75
    iksa
    0.71
    otte
    0.69
    adee
    0.69
     चौटाला
    0.68
     হিন্দুদের
    0.68
    Activations Density 0.006%

    No Known Activations