© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191241
    Prev
    Next
    INDEX
    Explanations

    class, alcohol, private

    np_acts-logits-general · gemini-2.5-flash-lite

    sexual content or acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    不仅
    0.36
    9
    0.34
    ie
    0.34
    不但
    0.34
    iegel
    0.33
    5
    0.32
     illetve
    0.32
    7
    0.32
    8
    0.32
     snd
    0.31
    POSITIVE LOGITS
    இவர்
    0.39
     admirable
    0.37
     gehören
    0.36
    疾患
    0.36
     ندارد
    0.36
     avant
    0.35
    亟
    0.35
     बेरोजगार
    0.34
    者は
    0.34
    年は
    0.34
    Activations Density 0.002%

    No Known Activations