© 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. 40717
    Prev
    Next
    INDEX
    Explanations

    linkage

    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
     vértice
    1.37
    чкой
    1.27
     itibaren
    1.27
     sexes
    1.24
    સ
    1.24
     Dislocations
    1.23
    <0xA4>
    1.23
    iyoruz
    1.23
    atán
    1.21
    ocomplete
    1.20
    POSITIVE LOGITS
    в
    1.21
     torr
    1.13
    ব
    1.11
    ాయ
    1.06
     berm
    1.05
     diel
    1.05
    ت
    1.05
    ત
    1.05
    પ
    1.03
    वे
    1.02
    Activations Density 0.000%

    No Known Activations