© 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. 220931
    Prev
    Next
    INDEX
    Explanations

    fish do, stories we, died and, told do

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

    staring blankly, phi(r_ij) calculation

    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
    ैर
    0.54
    قب
    0.50
     Surv
    0.46
     italiani
    0.46
    ENTY
    0.46
    ꯃ
    0.45
     ettiği
    0.45
    imensional
    0.45
    ெமி
    0.44
     उपसर्ग
    0.44
    POSITIVE LOGITS
    orm
    0.41
     שט
    0.41
    ansen
    0.41
     cash
    0.40
    writeToFile
    0.40
    rown
    0.40
    ведено
    0.40
     ကျွန်
    0.40
    自助
    0.39
    >[]
    0.39
    Activations Density 0.000%

    No Known Activations