© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3270
    Prev
    Next
    INDEX
    Explanations

    ai safety and ethical guidelines

    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
     USED
    0.34
    ϫ
    0.32
     cutest
    0.31
    されました
    0.30
    乸
    0.30
     nær
    0.30
    樖
    0.30
     hábito
    0.29
    ϩ
    0.29
     তুলনা
    0.29
    POSITIVE LOGITS
     and
    0.44
     Hum
    0.35
    aras
    0.34
    ora
    0.33
     offens
    0.33
     or
    0.31
    ab
    0.31
    and
    0.31
     In
    0.31
    acat
    0.31
    Activations Density 0.394%

    No Known Activations