© 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. 70587
    Prev
    Next
    INDEX
    Explanations

    make patent or worse

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

    language and flow

    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
    馨
    0.54
    ví
    0.49
     längst
    0.47
    v
    0.47
    ड्ड
    0.44
    c
    0.44
     Vorg
    0.44
    イ
    0.44
     colds
    0.43
    یکی
    0.43
    POSITIVE LOGITS
     раство
    0.50
     తేదీ
    0.49
     площа
    0.48
     পরিবার
    0.47
     જેના
    0.47
     взаимодействие
    0.47
     определя
    0.46
     страхо
    0.46
     पेड़
    0.46
     மகிழ்ச்ச
    0.46
    Activations Density 0.002%

    No Known Activations