© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205134
    Prev
    Next
    INDEX
    Explanations

    size and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite

    Rich Dad Poor Dad

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     মৃত্য
    0.46
     abnormalities
    0.45
    希
    0.45
     discontinuities
    0.45
     abnormal
    0.43
     জের
    0.43
     unsatisfied
    0.42
     了
    0.42
     unsol
    0.42
     unresolved
    0.42
    POSITIVE LOGITS
    อาหาร
    0.57
    сле
    0.52
    ศ
    0.49
     しっかり
    0.48
    ®,
    0.48
     열심히
    0.48
     pues
    0.46
    *,
    0.46
    пресс
    0.45
    ставка
    0.44
    Activations Density 0.000%

    No Known Activations