© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 164870
    Prev
    Next
    INDEX
    Explanations

    muscle vibration

    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
     щ
    0.41
    вре
    0.41
    ಚಿತ
    0.40
    тель
    0.40
    ঠু
    0.39
    ссов
    0.39
    менить
    0.39
    ល់
    0.38
     солдат
    0.38
    atius
    0.37
    POSITIVE LOGITS
     Strings
    0.43
     ==
    0.40
     cine
    0.38
    ুর
    0.38
     Scorsese
    0.38
    怀
    0.38
     Winners
    0.37
     Serif
    0.37
    Strings
    0.37
     সুবিধা
    0.37
    Activations Density 0.002%

    No Known Activations