© 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. 31-GEMMASCOPE-2-RES-262K
    7. 29673
    Prev
    Next
    INDEX
    Explanations

    appearance and sensory details

    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
     de
    0.47
     worldwide
    0.43
    {\'
    0.42
     Worldwide
    0.41
     større
    0.41
    🏁
    0.39
    are
    0.39
    ..</
    0.39
    Worldwide
    0.38
    ofa
    0.38
    POSITIVE LOGITS
     మొక్క
    0.47
     반지름
    0.46
     başlayalım
    0.45
     PLANTS
    0.44
     antifungal
    0.44
     mutta
    0.42
     dragState
    0.42
    icuously
    0.41
    虻
    0.41
    ränkt
    0.41
    Activations Density 0.010%

    No Known Activations