© 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. 37481
    Prev
    Next
    INDEX
    Explanations

    counters and pages

    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
    s
    0.51
    ড়াল
    0.43
     Tori
    0.42
    snake
    0.41
    sag
    0.41
    shoe
    0.41
     Sag
    0.41
    กลาง
    0.41
    Ordinal
    0.40
    blood
    0.40
    POSITIVE LOGITS
     REGIUNI
    0.51
     場合
    0.47
    在這裡
    0.45
    作
    0.45
    餡
    0.44
    每次
    0.43
     TRANSPORTURI
    0.43
    年在
    0.42
    PLE
    0.41
    ΡΟ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.