© 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. 41386
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ião
    1.34
    ität
    1.23
    eing
    1.20
    e
    1.16
    lichkeit
    1.13
    ah
    1.11
    cluding
    1.10
    ang
    1.09
    ง่าย
    1.09
    үм
    1.07
    POSITIVE LOGITS
    그리고
    1.27
    ム
    1.23
    は何
    1.15
    О
    1.13
     І
    1.09
     і
    1.09
    EXCLUSIVE
    1.09
    Assalamualaikum
    1.05
    Avec
    1.05
    Attk
    1.03
    Activations Density 0.000%

    No Known Activations