© 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. 5046
    Prev
    Next
    INDEX
    Explanations

    societal harm avoidance

    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
     impresses
    1.67
     praise
    1.64
     приятно
    1.61
     nghiệm
    1.59
     impressed
    1.57
     pozy
    1.57
     favorite
    1.56
     favorites
    1.55
     excellence
    1.51
    靈
    1.49
    POSITIVE LOGITS
    Climate
    1.24
     IPCC
    1.23
     exacerbate
    1.19
    climate
    1.18
     apocalypse
    1.12
     exacerb
    1.10
     Inequality
    1.09
     pandemics
    1.08
     earthquakes
    1.08
     urgente
    1.07
    Activations Density 0.292%

    No Known Activations