© 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. 134494
    Prev
    Next
    INDEX
    Explanations

    describing states or qualities

    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
     VR
    0.43
     ${
    0.42
    ’
    0.41
     obviously
    0.38
     inú
    0.38
    哪怕
    0.38
    你说
    0.37
     pretty
    0.37
     cosidd
    0.36
     Sü
    0.36
    POSITIVE LOGITS
    渊
    0.44
     посмотре
    0.42
    ವಿಧ
    0.42
    टो
    0.41
     моду
    0.41
     entrant
    0.40
    номо
    0.40
    図柄
    0.40
    覗
    0.40
     чисто
    0.40
    Activations Density 0.002%

    No Known Activations