© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42416
    Prev
    Next
    INDEX
    Explanations

    action movies

    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
    ك
    1.17
    이면
    1.12
    ન
    1.12
    िनल
    1.11
     foncé
    1.11
    ल
    1.10
    కుంది
    1.08
    旳
    1.07
    adanam
    1.03
    тность
    1.02
    POSITIVE LOGITS
    li
    1.13
    ara
    1.04
     Enzymes
    1.03
     enzymes
    1.02
    ą
    1.02
    ri
    1.01
    ı
    1.01
     they
    0.98
    TS
    0.97
     barley
    0.96
    Activations Density 0.003%

    No Known Activations