© 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. 164679
    Prev
    Next
    INDEX
    Explanations

    historical events and specific topics

    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
    agra
    0.44
    ff
    0.40
    itle
    0.39
     বিবিসির
    0.38
    %;">
    0.38
     पुस्त
    0.38
     revised
    0.37
     Vishnu
    0.37
     знаешь
    0.36
     updater
    0.36
    POSITIVE LOGITS
    Santiago
    0.44
     नोटबुक
    0.42
     「
    0.41
    gangenheit
    0.40
     cuda
    0.40
    Expr
    0.39
     devoir
    0.39
    Ordinate
    0.38
     chronicle
    0.38
    Charl
    0.38
    Activations Density 0.005%

    No Known Activations