© 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. 12067
    Prev
    Next
    INDEX
    Explanations

    straws

    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
    ى
    1.84
    ی
    1.77
    it
    1.76
     sebab
    1.53
     axioms
    1.51
     migli
    1.48
    ور
    1.48
     saws
    1.47
    которые
    1.46
    ﺘ
    1.46
    POSITIVE LOGITS
    ında
    1.90
    ının
    1.74
    d
    1.73
    ん
    1.69
    ların
    1.56
    llä
    1.55
    actory
    1.53
    sm
    1.51
    screen
    1.50
    sen
    1.45
    Activations Density 0.001%

    No Known Activations