© 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. 31-GEMMASCOPE-2-RES-65K
    7. 51130
    Prev
    Next
    INDEX
    Explanations

    durability and duration

    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_31_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
    長期
    0.55
    ৬
    0.49
    ការព
    0.48
    бира
    0.48
    -\
    0.45
    \}
    0.45
     времени
    0.45
    Delay
    0.45
     দূরে
    0.44
    睡眠
    0.44
    POSITIVE LOGITS
     trademarks
    0.57
     બ
    0.55
     ef
    0.54
     pigments
    0.54
     stucco
    0.54
    يق
    0.53
    ك
    0.52
     टिका
    0.51
    ią
    0.51
     surfactants
    0.51
    Activations Density 0.022%

    No Known Activations