© 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. 8018
    Prev
    Next
    INDEX
    Explanations

    Simplicity, Chinese, venue, deeply

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

    Chinese conjunctions and prepositions

    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
     машиналары
    0.55
     машиналарын
    0.52
     삽니다
    0.47
    кансер
    0.46
     ordinairement
    0.45
    鲔
    0.45
     뭔
    0.45
    铐
    0.45
    烃
    0.45
    Ꮩ
    0.44
    POSITIVE LOGITS
    一方面
    0.53
    据悉
    0.52
     dazzling
    0.48
     deeply
    0.45
     Chinese
    0.45
    早在
    0.45
     longing
    0.44
    借助
    0.43
    venue
    0.43
    凭借
    0.43
    Activations Density 0.043%

    No Known Activations