© 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. 5100
    Prev
    Next
    INDEX
    Explanations

    understanding perspective and morals

    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
     method
    2.16
     Method
    2.06
     **
    1.84
    egen
    1.83
     Im
    1.82
    ramer
    1.78
     highlighting
    1.77
    ort
    1.76
    昀
    1.76
     script
    1.75
    POSITIVE LOGITS
    此同时
    2.76
    регистри
    2.39
    ھی
    2.37
     consenting
    2.29
     fizik
    2.26
    ртуа
    2.18
     conversar
    2.17
     caminar
    2.15
    вичай
    2.14
     clases
    2.14
    Activations Density 0.011%

    No Known Activations