© 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. 120931
    Prev
    Next
    INDEX
    Explanations

    speaking or asking why

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

    question and explanation

    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
    }}(-
    0.50
     動
    0.48
    ინ
    0.45
     extraction
    0.44
    してお
    0.44
    ოლოგი
    0.44
    洳
    0.43
     რო
    0.42
     როგორც
    0.42
     ㅣ
    0.42
    POSITIVE LOGITS
    ÃO
    0.50
    क्यों
    0.47
    iendo
    0.46
    为什么要
    0.45
    难道
    0.45
     cuál
    0.44
    qué
    0.44
    графи
    0.44
     tão
    0.44
    为什么
    0.44
    Activations Density 0.001%

    No Known Activations