© 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. 209797
    Prev
    Next
    INDEX
    Explanations

    looking toward

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

    unexpectedly surprising

    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
     мали
    0.54
     χαρακτη
    0.51
     нәрсә
    0.50
    😡
    0.50
    🥎
    0.49
     грошы
    0.48
     губернатора
    0.48
    ्ठा
    0.47
     ничек
    0.47
    맟
    0.47
    POSITIVE LOGITS
     surprisingly
    0.46
    道
    0.45
     ironically
    0.45
     unexpectedly
    0.44
    路
    0.44
     neue
    0.44
     nouvelles
    0.43
     dibujos
    0.43
     bulun
    0.43
     العامة
    0.42
    Activations Density 0.000%

    No Known Activations