© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11516
    Prev
    Next
    INDEX
    Explanations

    feedback request

    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_9_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
     regimens
    1.67
    𝙏
    1.63
     Ingeniería
    1.62
     subtypes
    1.59
    𝙋
    1.59
     ooz
    1.55
     imprison
    1.54
     Ос
    1.53
    Да
    1.52
    Բ
    1.52
    POSITIVE LOGITS
    t
    1.81
    in
    1.68
    el
    1.65
    e
    1.64
    et
    1.63
    l
    1.48
    ite
    1.48
    as
    1.41
    ik
    1.40
    broken
    1.39
    Activations Density 0.000%

    No Known Activations