© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12689
    Prev
    Next
    INDEX
    Explanations

    namely, that is, called

    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_40_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
     сколько
    0.40
    だけでも
    0.39
     cometido
    0.38
     koliko
    0.38
    多少
    0.37
    的一些
    0.37
    那么多
    0.36
    丼
    0.36
     categorization
    0.35
    oty
    0.35
    POSITIVE LOGITS
    那就是
    0.93
     namely
    0.89
     yaitu
    0.84
    namely
    0.82
    就是
    0.76
    คือ
    0.76
     Namely
    0.68
    可以是
    0.68
     คือ
    0.68
     就是
    0.66
    Activations Density 0.038%

    No Known Activations