© 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. 133629
    Prev
    Next
    INDEX
    Explanations

    said north limit

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

    behavioral techniques, modification, layout recalculation

    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
     en
    0.50
     Besançon
    0.47
    Ws
    0.46
    يد
    0.46
    gallery
    0.46
     കാണ
    0.46
    ][
    0.46
     بسم
    0.45
     telefon
    0.45
     reconstruct
    0.45
    POSITIVE LOGITS
     stratég
    0.46
    永远
    0.45
     стратеги
    0.44
    都没
    0.43
    چھا
    0.43
     стратегия
    0.43
    囵
    0.43
     Journalism
    0.43
     Existen
    0.43
     interdependence
    0.42
    Activations Density 0.000%

    No Known Activations