© 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. 94457
    Prev
    Next
    INDEX
    Explanations

    extent of

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

    public exposure, humiliation, forced play

    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
    tf
    0.51
    oarece
    0.50
    ేవ
    0.49
    дон
    0.48
    िक्स
    0.47
    "):
    0.46
    शो
    0.45
     ""`
    0.45
    "?:
    0.45
    inherit
    0.44
    POSITIVE LOGITS
     protagonisti
    0.48
     dort
    0.43
     merhaba
    0.43
     protagonista
    0.43
     అక్కడ
    0.42
     fous
    0.42
     rifer
    0.41
    探讨
    0.41
     Singapura
    0.40
     direta
    0.40
    Activations Density 0.001%

    No Known Activations