© 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. 71131
    Prev
    Next
    INDEX
    Explanations

    business, product features, and descriptions

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

    academic, financial, and technical terms

    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
     enterr
    0.50
     edi
    0.47
    꾿
    0.46
    эд
    0.45
    getPlayer
    0.44
     Среди
    0.44
    իր
    0.43
     Олег
    0.43
    ир
    0.43
    तम
    0.43
    POSITIVE LOGITS
    s
    0.50
    OFFSET
    0.50
    x
    0.49
    1
    0.45
    ined
    0.44
     Grand
    0.43
     Brun
    0.43
     schöne
    0.43
     McClure
    0.43
     blushed
    0.43
    Activations Density 0.000%

    No Known Activations