© 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. 97963
    Prev
    Next
    INDEX
    Explanations

    required where

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

    increasing competition and potential

    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
    buty
    0.49
     Missouri
    0.47
     scrap
    0.46
    ;
    0.46
    urant
    0.46
    ugh
    0.45
     Pennsylvania
    0.44
    okee
    0.44
     miniature
    0.43
     ښ
    0.43
    POSITIVE LOGITS
    ньо
    0.45
     SafeArea
    0.45
    ционе
    0.44
    愤
    0.42
    桃
    0.40
    носит
    0.39
    룀
    0.39
     artículo
    0.39
    вал
    0.39
    ленная
    0.39
    Activations Density 0.000%

    No Known Activations