© 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. 182758
    Prev
    Next
    INDEX
    Explanations

    schools, from a city, single storey

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

    women's perspectives

    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
    آخر
    0.48
     celeb
    0.46
    ِ
    0.45
     America
    0.44
     limestone
    0.43
     Today
    0.43
     Last
    0.42
    Yesterday
    0.41
    珊
    0.41
     Yesterday
    0.41
    POSITIVE LOGITS
    LPTMR
    0.54
     Bakufu
    0.53
     narcot
    0.52
    positroid
    0.52
     виды
    0.51
     ば
    0.51
    flowLayoutPanel
    0.50
     plabic
    0.49
     главе
    0.49
    giver
    0.49
    Activations Density 0.000%

    No Known Activations