© 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. 208451
    Prev
    Next
    INDEX
    Explanations

    legal terms, definitions, and dates

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

    generating code

    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
    It
    0.54
    Re
    0.47
    Hours
    0.46
    An
    0.45
    Not
    0.44
    Im
    0.43
    Displays
    0.43
     ώ
    0.43
    Networks
    0.43
    ل
    0.43
    POSITIVE LOGITS
    님의
    0.51
    themealdb
    0.50
    님이
    0.47
     Wordsworth
    0.46
     पड़ेंगे
    0.46
     दीजिएगा
    0.45
    hitth
    0.45
    ที่ดี
    0.44
     LoginPage
    0.44
     Pasal
    0.44
    Activations Density 0.000%

    No Known Activations