© 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. 198627
    Prev
    Next
    INDEX
    Explanations

    violations or mistakes

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

    privacy violation and unauthorized access

    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
    is
    0.59
    0.58
    |
    0.45
    ..
    0.44
     constant
    0.43
    iter
    0.41
    Deque
    0.41
    --
    0.41
     narrowing
    0.41
     |
    0.41
    POSITIVE LOGITS
     нарушения
    0.64
     violate
    0.57
     нарушение
    0.57
     استعمال
    0.54
     verlassen
    0.54
     violación
    0.54
     ته
    0.54
    𝙩
    0.54
     переви
    0.54
     vutt
    0.53
    Activations Density 0.000%

    No Known Activations