© 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. 15365
    Prev
    Next
    INDEX
    Explanations

    us

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

    common phrases following specific words

    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
     have
    0.42
    ﾍ
    0.41
    Daddy
    0.40
     understand
    0.40
    Jupiter
    0.39
    Pets
    0.38
     prolifer
    0.38
    ၻ
    0.38
    fortun
    0.38
    ेंगू
    0.38
    POSITIVE LOGITS
     تیز
    0.61
    odnev
    0.54
     रोकना
    0.52
     Jeżeli
    0.52
     έως
    0.52
     ().
    0.51
     एवं
    0.50
     विरुद्ध
    0.50
     पहुंचा
    0.50
    ancellation
    0.50
    Activations Density 0.000%

    No Known Activations