© 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. 74441
    Prev
    Next
    INDEX
    Explanations

    scheduled visit, dog obeys, Marlowe says

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

    numbers and formatting

    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
    醤油
    0.49
    状態
    0.48
    gif
    0.47
    ｓ
    0.46
    ramer
    0.45
    チョコレート
    0.45
     KQkq
    0.44
    スペシャル
    0.43
    囧
    0.42
    🦀
    0.42
    POSITIVE LOGITS
     ഓർ
    0.55
    挹
    0.54
     plataformas
    0.50
    নির্
    0.48
     treinamento
    0.48
    োগ্র
    0.47
     espécie
    0.47
     filtros
    0.46
     pendekatan
    0.46
    ادة
    0.46
    Activations Density 0.000%

    No Known Activations