© 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. 146756
    Prev
    Next
    INDEX
    Explanations

    dataset URLs, postgres URLs

    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
    gebnis
    0.69
    def
    0.69
    鴎
    0.69
    죽
    0.68
    मर
    0.67
    出的
    0.65
    .(*
    0.63
     ফাইন
    0.62
    ผสม
    0.62
     považ
    0.61
    POSITIVE LOGITS
    Nas
    0.74
     nas
    0.68
     maybe
    0.68
     Web
    0.67
    Perhaps
    0.67
    ቋ
    0.64
     rotates
    0.64
     Suppliers
    0.64
     peasant
    0.63
     Peas
    0.63
    Activations Density 0.003%

    No Known Activations