© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61708
    Prev
    Next
    INDEX
    Explanations

    exclamations and surprises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    足够的
    0.47
     Frankly
    0.44
    偶尔
    0.44
     Preferably
    0.43
     সুদর্শন
    0.41
    乏
    0.40
    evším
    0.39
     একটু
    0.39
    шон
    0.39
     নানান
    0.39
    POSITIVE LOGITS
    ！
    0.53
     ternyata
    0.49
    まさ
    0.45
    สัญญาณ
    0.45
    !!!!!!
    0.45
     mobilization
    0.44
    ！」
    0.43
    竟然
    0.43
    ಿದ್ದಾನೆ
    0.42
     mobilizing
    0.41
    Activations Density 0.043%

    No Known Activations