© 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. 41485
    Prev
    Next
    INDEX
    Explanations

    image processing

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

    unique symbols and values

    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
    ederal
    0.46
    ї
    0.45
    pre
    0.44
    éph
    0.43
    深受
    0.43
    ⅼ
    0.43
    ars
    0.42
    স্টার
    0.42
    modes
    0.42
    sur
    0.41
    POSITIVE LOGITS
     UserManager
    0.50
     Gastroenter
    0.49
     Ophthalmology
    0.46
     Gegenwart
    0.46
     Specialties
    0.45
     specialties
    0.45
     ज्ये
    0.45
    핌
    0.45
     MBP
    0.44
     मैं
    0.44
    Activations Density 0.000%

    No Known Activations