© 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. 69784
    Prev
    Next
    INDEX
    Explanations

    modern technology, continuously monitors, dramatic footage

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

    debunking conspiracy theories

    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
     favor
    0.50
     plac
    0.45
    u
    0.44
    er
    0.44
     ruin
    0.43
    r
    0.43
     homestead
    0.43
    ován
    0.43
    ad
    0.43
    km
    0.42
    POSITIVE LOGITS
    ニー
    0.52
     астро
    0.50
    エリ
    0.49
     Бі
    0.48
     орке
    0.47
     \\..
    0.47
     감독
    0.46
    ビ
    0.46
    ਹ
    0.46
     парла
    0.46
    Activations Density 0.001%

    No Known Activations