© 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. 234726
    Prev
    Next
    INDEX
    Explanations

    keeps the

    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
     изменение
    0.49
     maupun
    0.47
    <0xE3>
    0.45
    攙
    0.45
    結合
    0.45
    金
    0.44
     보유
    0.43
    分析
    0.43
    輸入
    0.43
    แปลง
    0.43
    POSITIVE LOGITS
     CHRIST
    0.57
     truths
    0.50
    CHRIST
    0.47
     բ
    0.47
    rā
    0.45
     christ
    0.44
     تَ
    0.44
    »
    0.44
     إِن
    0.44
    niki
    0.43
    Activations Density 0.001%

    No Known Activations