© 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. 35739
    Prev
    Next
    INDEX
    Explanations

    legal action or lawsuit

    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
     vigt
    1.09
     Haring
    1.06
    leitung
    1.05
    hoog
    1.04
    Ι
    1.04
     Season
    1.03
     veze
    1.03
     chois
    1.01
    Kontakt
    1.00
     Cadastro
    1.00
    POSITIVE LOGITS
    ا
    1.54
    ्स
    1.52
    า
    1.47
    ת
    1.45
    ים
    1.35
    ان
    1.34
    א
    1.20
    اس
    1.17
    ка
    1.14
    ो
    1.14
    Activations Density 0.014%

    No Known Activations