© 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. 49682
    Prev
    Next
    INDEX
    Explanations

    saving money and time

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

    geometric shapes and fonts

    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
    ...
    0.54
    Avatar
    0.50
     Avatar
    0.46
    :
    0.46
    ",
    0.46
    n
    0.46
    https
    0.46
     Google
    0.46
     youre
    0.46
     University
    0.45
    POSITIVE LOGITS
     geometrical
    0.57
     геометри
    0.57
    ziger
    0.50
     trueMap
    0.49
     seiner
    0.49
     конкурс
    0.49
     годом
    0.48
    觟
    0.48
     фору
    0.48
     adhipp
    0.47
    Activations Density 0.001%

    No Known Activations