© 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. 188398
    Prev
    Next
    INDEX
    Explanations

    able to something

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

    financial goals and monitoring your time

    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
    #[
    0.51
     シュ
    0.51
     ഒരു
    0.50
    covariant
    0.49
    ”।
    0.48
    ।''
    0.48
    Ї
    0.47
    talet
    0.47
    <unused27>
    0.46
    LEV
    0.46
    POSITIVE LOGITS
     envol
    0.42
     одежда
    0.41
    imwrite
    0.41
     alternatives
    0.41
    imani
    0.41
     amendments
    0.40
     underworld
    0.40
     favourites
    0.40
     racked
    0.40
     organiz
    0.39
    Activations Density 0.000%

    No Known Activations