© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147992
    Prev
    Next
    INDEX
    Explanations

    prepositions and code fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_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
     држа
    0.63
     Du
    0.63
     actually
    0.60
    बाजी
    0.60
    罨
    0.58
     drž
    0.57
     brutally
    0.57
     pels
    0.57
    íssimo
    0.57
     unmatched
    0.57
    POSITIVE LOGITS
     onLoad
    0.74
    ങ്കി
    0.71
    ịa
    0.71
    쇼
    0.70
     Penet
    0.69
     Sherwood
    0.68
     pyautogui
    0.67
     шу
    0.67
    container
    0.66
    voit
    0.65
    Activations Density 0.002%

    No Known Activations