© 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. 71242
    Prev
    Next
    INDEX
    Explanations

    target screening

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

    harmful or hateful content

    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
     ejercer
    0.52
     آگے
    0.47
    رو
    0.47
    اح
    0.46
    ަ
    0.46
     alarming
    0.45
     endeavour
    0.44
     alarmed
    0.44
     anteriormente
    0.44
     gider
    0.44
    POSITIVE LOGITS
     Garbage
    0.47
     GLOB
    0.47
     高さ
    0.46
     Drop
    0.46
     доме
    0.46
    飧
    0.45
    期の
    0.44
    食品
    0.43
     हायर
    0.43
     LOWER
    0.43
    Activations Density 0.000%

    No Known Activations