© 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. 159799
    Prev
    Next
    INDEX
    Explanations

    sexually explicit material and rentals

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

    Matrices, Catalan, evaluation

    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
    Not in Any Lists

    No Comments

    Negative Logits
     isten
    0.52
     Controllers
    0.47
    爬
    0.47
     not
    0.45
     Symmetry
    0.45
     камер
    0.43
     malu
    0.43
    мно
    0.42
    íbrio
    0.42
    𝐇
    0.42
    POSITIVE LOGITS
    বাসী
    0.48
    ススメ
    0.46
    штейн
    0.45
    जीत
    0.43
     行っ
    0.43
     Zool
    0.43
    പ്പെട്ട്
    0.42
    ア
    0.42
    ウェット
    0.41
    सो
    0.41
    Activations Density 0.001%

    No Known Activations