© 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. 128163
    Prev
    Next
    INDEX
    Explanations

    selected, coins, gold, application

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

    describing functions, roles, or qualities

    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
    ಶ
    0.58
    なども
    0.49
    メール
    0.48
    庫
    0.47
    울
    0.45
    資料
    0.45
    とか
    0.45
    ﾃ
    0.45
    자
    0.45
    詠
    0.45
    POSITIVE LOGITS
     NaOH
    0.51
     कन्न
    0.48
     origem
    0.47
     Kannada
    0.47
     आँख
    0.46
     ru
    0.45
     fuit
    0.44
     అయిన
    0.44
     จง
    0.44
     ہوا۔
    0.44
    Activations Density 0.000%

    No Known Activations