© 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. 176040
    Prev
    Next
    INDEX
    Explanations

    new project

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

    common, disappear, from, vast, shorter

    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
     وده
    0.46
    0
    0.43
    assert
    0.42
     cnt
    0.42
     asserts
    0.42
    韻
    0.42
    يم
    0.41
    也會
    0.40
     assert
    0.40
    miš
    0.40
    POSITIVE LOGITS
     गर
    0.47
     استخدام
    0.47
     زمین
    0.46
    হারা
    0.46
     авиа
    0.46
    भूमि
    0.46
    ז
    0.46
     aprovechar
    0.45
    уса
    0.45
    یکن
    0.45
    Activations Density 0.001%

    No Known Activations