© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 106844
    Prev
    Next
    INDEX
    Explanations

    time, guidelines, activities, reasonable, pods

    np_acts-logits-general · gemini-2.5-flash-lite

    dialogue writing and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     classe
    0.54
    骧
    0.50
    樣
    0.50
    想像
    0.48
    μι
    0.48
    ണിയ
    0.48
     erre
    0.48
     unités
    0.48
     immagin
    0.48
    स
    0.48
    POSITIVE LOGITS
    {},
    0.50
    atchewan
    0.45
    ypress
    0.44
    rop
    0.43
    äl
    0.43
    enos
    0.43
    aw
    0.43
    ow
    0.42
    otrans
    0.42
    ois
    0.42
    Activations Density 0.001%

    No Known Activations