© 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. 10789
    Prev
    Next
    INDEX
    Explanations

    parenthetical descriptions/definitions

    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
     I
    1.40
    ;
    1.28
     is
    1.16
     (
    1.13
     /
    1.13
    :
    1.10
     =
    1.09
    R
    1.09
    W
    1.08
     L
    1.07
    POSITIVE LOGITS
     saque
    1.00
    custList
    0.99
     clínicas
    0.99
    筺
    0.98
    ើញ
    0.98
    kräfte
    0.97
     svært
    0.96
    胰
    0.95
    躹
    0.95
     cuantos
    0.94
    Activations Density 1.102%

    No Known Activations