© 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. 3824
    Prev
    Next
    INDEX
    Explanations

    sheep

    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
    stion
    1.54
    ر
    1.44
    ্পনিক
    1.37
    ש
    1.30
     athe
    1.28
    囃
    1.28
    要
    1.25
    یاں
    1.23
     wrath
    1.23
     adduced
    1.23
    POSITIVE LOGITS
    or
    1.98
    ed
    1.60
    ौनक
    1.60
    ات
    1.58
    Shim
    1.57
    ного
    1.55
    ંદ
    1.53
    Ста
    1.52
    as
    1.52
    ﻥ
    1.52
    Activations Density 0.001%

    No Known Activations