© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 12076
    Prev
    Next
    INDEX
    Explanations

    toward a goal or state

    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
    Negative Logits
    cdot
    1.60
    ことを
    1.60
    woven
    1.57
     traz
    1.56
    .
    1.56
     مساء
    1.54
     Fractal
    1.53
     للغاية
    1.50
    ال
    1.49
     promov
    1.48
    POSITIVE LOGITS
    त
    2.94
    т
    2.52
    น
    2.48
    ט
    2.42
    س
    2.14
    ת
    2.14
    ل
    2.09
    นั่ง
    2.02
    kings
    1.99
    นิยม
    1.96
    Activations Density 0.010%

    No Known Activations