© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48635
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    简化
    0.45
     Camps
    0.40
     simpl
    0.40
    简
    0.40
    [-
    0.39
    oderma
    0.39
     loc
    0.38
     simple
    0.37
     Coin
    0.36
     simplified
    0.36
    POSITIVE LOGITS
     අධ
    0.39
    綾
    0.38
     धैर्य
    0.38
     alakalı
    0.38
    isl
    0.37
    мпаваць
    0.37
    ards
    0.36
    ichtung
    0.34
     متاثر
    0.34
    擇
    0.34
    Activations Density 0.014%

    No Known Activations