© 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. 14680
    Prev
    Next
    INDEX
    Explanations

    Y mouse position

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

    y coordinate assignment

    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
     unarmed
    0.46
     পুষ
    0.39
    ቀር
    0.38
     armed
    0.38
    LVector
    0.38
    ("")]
    0.37
     {[
    0.37
    {``
    0.36
    िस्तान
    0.36
    無需
    0.36
    POSITIVE LOGITS
     altura
    0.52
     высоту
    0.49
     ارتفاع
    0.47
     height
    0.46
     altitude
    0.46
     Höhe
    0.46
     Höhen
    0.45
     njegove
    0.45
     njegova
    0.43
     alturas
    0.43
    Activations Density 0.002%

    No Known Activations