© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    upward and downward movement

    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
    ade
    2.19
     común
    2.05
    e
    1.95
    ه
    1.94
    بيق
    1.85
    breed
    1.80
     жив
    1.80
     malesuada
    1.79
    glio
    1.77
     sagittis
    1.77
    POSITIVE LOGITS
    t
    2.69
    ../../
    2.42
    om
    2.19
    theless
    2.11
    ેલા
    2.06
    레
    1.96
    ર
    1.94
    ך
    1.90
    daughters
    1.88
    ેલ
    1.85
    Activations Density 0.026%

    No Known Activations