© 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. 207088
    Prev
    Next
    INDEX
    Explanations

    quantifying cost or time

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

    YouTubers scramble to distance

    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
    ignant
    0.44
     존재하는
    0.43
     capitalists
    0.42
     Islamist
    0.42
    chsler
    0.40
     현실
    0.40
    ႉ
    0.40
    champion
    0.39
    ರುತ್ತವೆ
    0.39
    많
    0.38
    POSITIVE LOGITS
     stessa
    0.55
     acela
    0.54
     birlikte
    0.54
     дорога
    0.52
     disposição
    0.52
     thậm
    0.51
     sred
    0.51
     antiga
    0.51
     sõ
    0.50
     bağlant
    0.50
    Activations Density 0.000%

    No Known Activations