© 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. 130574
    Prev
    Next
    INDEX
    Explanations

    path to or pathPage

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

    path to a file

    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
    t
    1.20
    ير
    1.01
    vý
    0.99
    ur
    0.95
    v
    0.93
    يف
    0.86
    ம்
    0.86
    tun
    0.85
    ere
    0.85
    ine
    0.84
    POSITIVE LOGITS
     path
    1.13
    ف
    1.13
    น
    1.10
    ب
    1.03
    ıları
    1.01
    ุ
    1.01
    с
    0.98
     you
    0.97
     경로
    0.96
     pathway
    0.93
    Activations Density 0.021%

    No Known Activations