© 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. 45419
    Prev
    Next
    INDEX
    Explanations

    common phrases with "while" or leading punctuation

    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
     n
    0.47
     football
    0.44
     invade
    0.44
     English
    0.42
     down
    0.42
     s
    0.41
     Window
    0.40
    royo
    0.40
     nearby
    0.40
     cycl
    0.39
    POSITIVE LOGITS
    牴
    0.45
    保持
    0.44
    朳
    0.43
    保有
    0.42
    航
    0.42
    價值
    0.42
    绘制
    0.41
    益
    0.41
    گن
    0.41
    OCITY
    0.41
    Activations Density 0.001%

    No Known Activations