© 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. 16-GEMMASCOPE-2-RES-16K
    7. 417
    Prev
    Next
    INDEX
    Explanations

    Starts of sentences with names

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

    specific strategies

    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_16_width_16k_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
    га
    0.81
    х
    0.74
    htmlspecialchars
    0.71
    four
    0.70
    γ
    0.68
    constants
    0.66
    the
    0.66
    postion
    0.66
    three
    0.64
    that
    0.62
    POSITIVE LOGITS
     Fiesta
    0.70
     Putri
    0.66
     Monate
    0.64
     Frau
    0.63
     Gazette
    0.63
     Hasta
    0.63
     Woman
    0.62
     Mama
    0.62
    ↵↵
    0.61
     Musik
    0.61
    Activations Density 0.414%

    No Known Activations