© 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. 7295
    Prev
    Next
    INDEX
    Explanations

    actions performed quickly

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

    pronoun performing action

    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
     není
    0.29
     ہونا
    0.29
     وجود
    0.29
    疼
    0.28
     nhiệm
    0.28
     vermeiden
    0.28
     sürec
    0.28
     त्यावेळी
    0.27
     ዓ
    0.26
    ㅀ
    0.26
    POSITIVE LOGITS
    เข้าไป
    0.43
     hurriedly
    0.42
     hastily
    0.41
    拿出
    0.36
    拿起
    0.36
     opened
    0.35
     quickly
    0.35
     walked
    0.35
    打开
    0.35
     gently
    0.35
    Activations Density 0.424%

    No Known Activations