© 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. 24-GEMMASCOPE-2-RES-262K
    7. 12634
    Prev
    Next
    INDEX
    Explanations

    ממני, מה, שאול

    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_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0.82
     characteristics
    0.62
     increased
    0.59
     trenches
    0.56
     improved
    0.55
    听
    0.55
     protective
    0.55
     experimental
    0.54
     emissions
    0.54
     average
    0.54
    POSITIVE LOGITS
     ה
    1.05
     עם
    1.05
     הכ
    1.04
     מה
    0.98
     לי
    0.98
     אם
    0.98
     מת
    0.96
     מר
    0.95
    ות
    0.95
     הת
    0.95
    Activations Density 0.000%

    No Known Activations