© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50136
    Prev
    Next
    INDEX
    Explanations

    unlocks capabilities

    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_65k_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
    recur
    0.39
     وګټ
    0.39
    Созда
    0.38
    𝑻
    0.38
    🫰
    0.38
    ইয়
    0.38
    Titulo
    0.38
    柊
    0.37
    粲
    0.37
     पीएचडी
    0.36
    POSITIVE LOGITS
     code
    0.51
     codes
    0.40
    ടിക്ക
    0.40
     suivantes
    0.39
     existence
    0.39
     optimize
    0.39
    codes
    0.38
    規格
    0.38
     존재하는
    0.38
     exists
    0.37
    Activations Density 0.002%

    No Known Activations