© 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. 120681
    Prev
    Next
    INDEX
    Explanations

    satellite internet

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

    Dynamic Island, integer, interval, beast

    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
    ش
    0.52
    ла
    0.47
    ج
    0.45
    را
    0.45
     конку
    0.44
     Uniform
    0.44
     Koff
    0.44
    ッシ
    0.43
    كري
    0.43
    سكري
    0.43
    POSITIVE LOGITS
    他对
    0.58
     இந்
    0.49
     maig
    0.49
    ylsulfanyl
    0.45
     இருந்தது
    0.45
     や
    0.44
     இவ்
    0.44
     läbi
    0.44
    ায়ণের
    0.44
     onay
    0.44
    Activations Density 0.000%

    No Known Activations