© 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. 248509
    Prev
    Next
    INDEX
    Explanations

    location names and phrases

    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
     ט
    0.57
     rept
    0.49
     ساعت
    0.49
    oul
    0.45
    ológicos
    0.45
     મોટી
    0.45
     مايو
    0.44
     چاپ
    0.44
     ساعة
    0.44
    СТ
    0.43
    POSITIVE LOGITS
     subscribers
    0.47
     Stockton
    0.46
     advertised
    0.46
    f
    0.45
    y
    0.45
     instructions
    0.44
    гід
    0.44
     লিখিয়াছেন
    0.44
    麸
    0.44
     JIS
    0.44
    Activations Density 0.000%

    No Known Activations