© 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. 18937
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    741741

    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
    Ө
    0.45
    WEB
    0.44
    њ
    0.43
    PRESS
    0.42
    hr
    0.41
    Web
    0.40
     лаборатор
    0.40
    UN
    0.40
    LIBRARY
    0.39
    х
    0.39
    POSITIVE LOGITS
     मोबाइल
    0.61
     móvil
    0.61
     ragazzo
    0.61
     mobile
    0.60
     móviles
    0.59
     Iphone
    0.58
     iPhone
    0.57
     iphone
    0.57
     Mobile
    0.55
     persoonlijke
    0.55
    Activations Density 0.021%

    No Known Activations