© 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. 50842
    Prev
    Next
    INDEX
    Explanations

    show you?

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

    targeted contexts

    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
    destino
    0.50
    玺
    0.49
    ćem
    0.49
    ግር
    0.47
    വി
    0.47
    पया
    0.47
    回顾
    0.47
    停车场
    0.46
    <unused675>
    0.46
    渴望
    0.46
    POSITIVE LOGITS
     (>
    0.48
     targeting
    0.45
     (=
    0.45
     color
    0.44
    の値
    0.44
     featuring
    0.43
     ratio
    0.43
     interval
    0.43
     pulp
    0.43
     values
    0.43
    Activations Density 0.000%

    No Known Activations