© 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. 51628
    Prev
    Next
    INDEX
    Explanations

    waiting list for pricing

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

    let me know

    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
    it
    0.49
    an
    0.45
    er
    0.45
    portrait
    0.44
    ма
    0.44
     образом
    0.43
     ек
    0.43
    ِر
    0.43
    ######
    0.43
     بخشی
    0.43
    POSITIVE LOGITS
     glucose
    0.49
     diesel
    0.45
     multic
    0.45
     Calcd
    0.45
     Daddy
    0.43
    )||
    0.43
    )[
    0.43
     conval
    0.41
     cardiomyocytes
    0.41
     CDT
    0.41
    Activations Density 0.000%

    No Known Activations