© 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. 212882
    Prev
    Next
    INDEX
    Explanations

    actions or conditions that exceed boundaries

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

    list comprehension closing bracket

    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
    ل
    0.77
    ル
    0.65
    بر
    0.55
    ラ
    0.55
    یل
    0.54
    الی
    0.51
    ハン
    0.50
    لیک
    0.49
     توسط
    0.49
    lern
    0.48
    POSITIVE LOGITS
     deviate
    0.49
    다라고
    0.43
     ఆరోగ్య
    0.42
     Masses
    0.40
    verture
    0.40
     Tablets
    0.40
     religiosa
    0.39
    *)
    0.39
     району
    0.39
     pondered
    0.39
    Activations Density 0.002%

    No Known Activations