© 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. 194937
    Prev
    Next
    INDEX
    Explanations

    sun god

    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
    තිය
    0.42
    ဿ
    0.41
    сор
    0.40
    ца
    0.38
     pund
    0.37
    carn
    0.37
    hite
    0.37
     compro
    0.37
     grav
    0.37
    ема
    0.36
    POSITIVE LOGITS
     Heavy
    0.56
     heavier
    0.54
     heaviest
    0.54
     heavy
    0.54
    lighter
    0.53
     lighter
    0.52
    重
    0.52
     lightest
    0.51
     سبک
    0.51
    Heavy
    0.50
    Activations Density 0.000%

    No Known Activations