© 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. 202147
    Prev
    Next
    INDEX
    Explanations

    inspired by experience

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

    acknowledges the statement

    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
     مسائل
    0.51
     جمل
    0.50
     كون
    0.46
     TAE
    0.46
     да
    0.46
     २
    0.45
     व
    0.45
     мат
    0.45
    ет
    0.44
     ニット
    0.44
    POSITIVE LOGITS
    淹
    0.50
    il
    0.49
    éné
    0.48
    clim
    0.46
    illä
    0.46
    ">{{
    0.46
    ಾವಣ
    0.45
    洗衣
    0.44
    ö
    0.44
     evaporation
    0.43
    Activations Density 0.001%

    No Known Activations