© 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. 192406
    Prev
    Next
    INDEX
    Explanations

    legal business and names

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

    non-English characters or code

    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
     cookware
    0.53
     ২৬
    0.50
     lifeguard
    0.46
     browsing
    0.45
     aplicação
    0.44
     band
    0.44
    㕕
    0.44
    ដែលមាន
    0.44
     licenci
    0.44
     মার্চ
    0.43
    POSITIVE LOGITS
    LowerCase
    0.47
    CharAt
    0.46
    汴
    0.46
    샷
    0.45
    르
    0.45
     பகை
    0.44
     поз
    0.43
    เฟ
    0.43
    uria
    0.43
    Assumption
    0.42
    Activations Density 0.000%

    No Known Activations