© 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. 114000
    Prev
    Next
    INDEX
    Explanations

    team, family, essentials, required, equipment

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

    identifying negative content or damage

    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
    Streaming
    0.44
    اہد
    0.43
     Corollary
    0.42
     તેમની
    0.42
    闿
    0.42
     discarded
    0.40
     Grou
    0.40
     Gaines
    0.40
    ・・・・
    0.40
    傑
    0.40
    POSITIVE LOGITS
    sek
    0.53
    trasound
    0.50
     iki
    0.49
    ‚
    0.48
    raz
    0.46
     tačiau
    0.46
    zyme
    0.46
     sek
    0.45
     kaliteli
    0.45
     hybrid
    0.45
    Activations Density 0.002%

    No Known Activations