© 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. 178270
    Prev
    Next
    INDEX
    Explanations

    sharing, commenting, posting

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

    API usage and inference

    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
    ᴋ
    0.46
     reorgan
    0.43
    меча
    0.41
    ức
    0.41
    κο
    0.40
     restructure
    0.40
    ueba
    0.40
     serangan
    0.40
    rik
    0.40
    hetto
    0.40
    POSITIVE LOGITS
     Nantucket
    0.50
    ၌
    0.49
     viszont
    0.49
     પાસે
    0.49
     únic
    0.48
     usato
    0.48
     กราบ
    0.48
     უფრო
    0.48
    竣
    0.47
     Shannon
    0.47
    Activations Density 0.001%

    No Known Activations