© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5068
    Prev
    Next
    INDEX
    Explanations

    bad or unhealthy things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Edmond
    1.48
    org
    1.48
     Moh
    1.43
    7
    1.42
     Peloton
    1.41
     org
    1.35
     Petro
    1.34
     Simon
    1.31
     Concordia
    1.30
     Stepan
    1.28
    POSITIVE LOGITS
    Bad
    1.64
     Bad
    1.48
     bad
    1.45
    bad
    1.41
     malos
    1.29
     baddies
    1.22
    BAD
    1.21
     unhealthy
    1.13
    坏
    1.12
     BAD
    1.09
    Activations Density 0.048%

    No Known Activations