© 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. 16-GEMMASCOPE-2-RES-262K
    7. 85406
    Prev
    Next
    INDEX
    Explanations

    register renaming

    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_16_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
     gezegd
    0.58
     gesagt
    0.55
    č
    0.54
    aches
    0.53
    ğ
    0.51
    棪
    0.51
     detto
    0.51
    比如說
    0.51
    eros
    0.50
     ধরন
    0.50
    POSITIVE LOGITS
    نا
    0.72
    ه‌ای
    0.64
    对
    0.61
    .
    0.59
    ONG
    0.58
    !
    0.57
    ΙΑ
    0.56
     ശക്ത
    0.55
    nä
    0.54
    رب
    0.54
    Activations Density 0.009%

    No Known Activations