© 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. 193643
    Prev
    Next
    INDEX
    Explanations

    multilingual words

    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
     Alf
    0.37
     pesta
    0.35
     мисте
    0.35
     घेत
    0.34
     feature
    0.33
     mont
    0.33
    ición
    0.33
     첨
    0.33
    OfMonth
    0.33
     Coffee
    0.33
    POSITIVE LOGITS
     lập
    0.39
     redeemed
    0.39
     سريع
    0.39
     결국
    0.38
    笏
    0.38
    ధాన
    0.38
     Dadurch
    0.38
     Maugin
    0.38
     স্ন
    0.37
     واکنش
    0.37
    Activations Density 0.000%

    No Known Activations