© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47649
    Prev
    Next
    INDEX
    Explanations

    forbidden or unsafe code practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ObjectIndex
    0.40
     ecma
    0.39
     strikes
    0.38
    SourceObject
    0.37
    Skippable
    0.36
    tku
    0.36
     якого
    0.36
    蝿
    0.36
     semicolon
    0.36
    柤
    0.35
    POSITIVE LOGITS
    no
    0.56
    forbidden
    0.46
    不允许
    0.44
     no
    0.42
     prohibiting
    0.42
    ни
    0.41
     forbid
    0.41
     forbade
    0.41
     प्रतिबंधित
    0.41
     proib
    0.40
    Activations Density 0.007%

    No Known Activations