© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41753
    Prev
    Next
    INDEX
    Explanations

    state of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    strasse
    1.34
    te
    1.30
    st
    1.28
    mental
    1.26
    ph
    1.25
    so
    1.21
     kelamin
    1.20
    ↵↵
    1.19
    teki
    1.17
     pasando
    1.16
    POSITIVE LOGITS
    एस
    1.68
    مي
    1.55
    こと
    1.54
    م
    1.51
    الصفحه
    1.43
    檛
    1.39
    人類
    1.35
    های
    1.34
    يل
    1.31
    مة
    1.30
    Activations Density 0.031%

    No Known Activations