© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12340
    Prev
    Next
    INDEX
    Explanations

    views expressed

    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_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
     Иногда
    0.47
    ਗਾ
    0.47
    ###############
    0.44
    を使って
    0.44
    leaves
    0.44
     paves
    0.43
    ##############
    0.43
     trusty
    0.43
     tipping
    0.43
     progenitor
    0.42
    POSITIVE LOGITS
    颈
    0.46
    න්
    0.46
    钛
    0.45
    炖
    0.45
    ש
    0.45
     katika
    0.42
    世纪
    0.42
    ɱ
    0.42
    在一个
    0.41
    诸
    0.41
    Activations Density 0.001%

    No Known Activations