© 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. 69140
    Prev
    Next
    INDEX
    Explanations

    worldwide potential

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

    focusing on intent

    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
    Lane
    0.47
    有两种
    0.46
    Worlds
    0.46
    əs
    0.44
     সবচেয়ে
    0.44
    न्यास
    0.44
    是没有
    0.43
    😶
    0.43
    这位
    0.42
    டைந்து
    0.42
    POSITIVE LOGITS
    ワ
    0.49
     I
    0.49
    ROUND
    0.46
     efectiva
    0.45
    スタイ
    0.44
     POM
    0.44
     Eth
    0.44
    ティー
    0.43
    紹介
    0.43
     jaar
    0.43
    Activations Density 0.002%

    No Known Activations