© 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. 76688
    Prev
    Next
    INDEX
    Explanations

    my buddy, your call, sharing service

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

    percentage, apartment, perks

    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
     아름
    0.47
     最后
    0.46
     谢
    0.45
     상세보기
    0.44
    藓
    0.44
    焐
    0.44
     联系
    0.43
    יר
    0.43
    र्
    0.42
    দিগকে
    0.42
    POSITIVE LOGITS
    zona
    0.47
     flota
    0.45
    apartment
    0.45
     Yucatán
    0.44
     salwar
    0.43
     Latino
    0.43
     tinct
    0.43
    statt
    0.42
     oils
    0.42
     híbr
    0.42
    Activations Density 0.001%

    No Known Activations