© 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. 174018
    Prev
    Next
    INDEX
    Explanations

    on Facebook, crossover hits

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

    proactive control or disruption

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aned
    0.53
    u
    0.50
    successor
    0.49
    time
    0.49
    ppu
    0.49
    लक
    0.48
    adn
    0.48
    ak
    0.47
    tenth
    0.47
    btree
    0.47
    POSITIVE LOGITS
     další
    0.45
     Manch
    0.45
     আসেনি
    0.45
     repas
    0.44
    席
    0.43
    піль
    0.43
     MÉ
    0.43
    來越
    0.42
     волосы
    0.42
     financeiros
    0.42
    Activations Density 0.001%

    No Known Activations