© 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. 170054
    Prev
    Next
    INDEX
    Explanations

    bookmarking a site

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

    harmful or explicit content

    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
    很多
    0.50
    y
    0.50
    娥
    0.48
    战争
    0.47
    他的
    0.45
     河
    0.45
    最
    0.45
    想要
    0.44
    小白
    0.44
    动
    0.43
    POSITIVE LOGITS
     gezond
    0.48
     میل
    0.48
     اص
    0.47
     edibles
    0.47
    fromRGB
    0.46
     boissons
    0.45
     নেতাদের
    0.44
    gouv
    0.44
    জ্জামান
    0.43
    hetics
    0.43
    Activations Density 0.002%

    No Known Activations