© 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. 36148
    Prev
    Next
    INDEX
    Explanations

    Nothing herein

    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
    ى
    1.63
    ta
    1.62
    in
    1.37
    ten
    1.34
    ");
    1.30
    ak
    1.29
    as
    1.26
    امہ
    1.24
    hellip
    1.19
    em
    1.17
    POSITIVE LOGITS
    м
    1.73
    т
    1.52
    მ
    1.48
    л
    1.46
    ר
    1.44
     nhiên
    1.41
     그다음에
    1.38
    מ
    1.35
    нце
    1.32
    лд
    1.30
    Activations Density 0.000%

    No Known Activations