© 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. 168369
    Prev
    Next
    INDEX
    Explanations

    . One, Helps, A, How

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

    connection or device requests

    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
    ურნ
    0.43
    颼
    0.42
     उपास
    0.41
    孙
    0.41
    ঘ
    0.40
    经典
    0.40
    样品
    0.40
    จริง
    0.40
     szen
    0.40
    дной
    0.39
    POSITIVE LOGITS
    ここは
    0.43
     latitude
    0.43
     কাছাকাছি
    0.43
     nahin
    0.43
     Latitude
    0.42
    ی
    0.41
     Jeffery
    0.41
     the
    0.41
     a
    0.40
    atschapp
    0.40
    Activations Density 0.000%

    No Known Activations