© 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. 200804
    Prev
    Next
    INDEX
    Explanations

    requirement or perhaps

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

    owning guns or hike

    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
    +
    0.50
     it
    0.48
     recognition
    0.46
     ne
    0.45
    :
    0.44
     drastic
    0.44
     healers
    0.44
     interdependence
    0.43
     well
    0.43
     automation
    0.43
    POSITIVE LOGITS
     শাজ
    0.54
     খাজ
    0.50
     পিতা
    0.49
    maxX
    0.49
    杩
    0.47
     грани
    0.46
     फाइनेंशियल
    0.46
     মিনিট
    0.46
     Wein
    0.45
     Фон
    0.45
    Activations Density 0.001%

    No Known Activations