© 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. 146209
    Prev
    Next
    INDEX
    Explanations

    offering follow-up actions

    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
     propon
    0.75
     অশ
    0.71
     azal
    0.71
     않으면
    0.68
    檴
    0.68
    ertid
    0.68
     Polytechn
    0.67
    modelVersion
    0.67
    erset
    0.66
    <unused424>
    0.66
    POSITIVE LOGITS
    ড়া
    0.71
     Crunch
    0.67
     predict
    0.66
    Address
    0.63
     try
    0.63
    ড়া
    0.63
    釉
    0.61
    <0xE3>
    0.61
     τελευτα
    0.61
    ଳ
    0.61
    Activations Density 0.004%

    No Known Activations