© 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. 158872
    Prev
    Next
    INDEX
    Explanations

    million years

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

    foreign language tokens

    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
    ar
    0.47
     Lark
    0.47
     Illustrations
    0.46
     Melody
    0.46
     Elast
    0.45
    ennial
    0.43
     (%
    0.43
    －
    0.43
     VM
    0.43
     OC
    0.43
    POSITIVE LOGITS
     quiso
    0.53
    এরপর
    0.52
    支払い
    0.52
     മാന
    0.51
     parcial
    0.49
    マッチ
    0.49
     sauvage
    0.49
    畠
    0.49
     parfois
    0.49
    トリ
    0.48
    Activations Density 0.000%

    No Known Activations