© 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. 219488
    Prev
    Next
    INDEX
    Explanations

    report update concerns correct any problems

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

    code related to division

    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
    StoreException
    0.54
    五十
    0.52
    濾
    0.52
    rün
    0.50
     ամ
    0.50
    滤
    0.50
    在日本
    0.50
     ৫৮
    0.50
    坦
    0.50
    অন্ত
    0.49
    POSITIVE LOGITS
     Muslim
    0.50
     terminus
    0.49
    ique
    0.48
    Muslim
    0.48
     quark
    0.47
     clone
    0.45
     Caucasus
    0.45
     HOMO
    0.45
     Leinster
    0.44
    ishes
    0.43
    Activations Density 0.001%

    No Known Activations