© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163861
    Prev
    Next
    INDEX
    Explanations

    screen printing

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

    charge, London, cm

    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
     ide
    0.54
     ete
    0.54
     vara
    0.53
     eta
    0.53
     are
    0.52
     ar
    0.51
     partial
    0.51
    是
    0.51
     UW
    0.50
    は
    0.50
    POSITIVE LOGITS
     квартиры
    0.62
     आक्रमण
    0.54
    cardia
    0.53
    unsqueeze
    0.51
    “-
    0.50
    quark
    0.50
    irken
    0.50
    বস্ত
    0.50
    wirkungen
    0.50
     Terbang
    0.49
    Activations Density 0.000%

    No Known Activations