© 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. 180800
    Prev
    Next
    INDEX
    Explanations

    financial, legal, or place names

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

    0 or related math

    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
    A
    0.55
     Water
    0.54
    S
    0.54
    Q
    0.52
    L
    0.50
     but
    0.49
     you
    0.49
     water
    0.48
    K
    0.48
    你会
    0.48
    POSITIVE LOGITS
     آہ
    0.56
     контек
    0.53
     dakkh
    0.52
    اگ
    0.50
     проведення
    0.49
     وہی
    0.49
     ਨਾਲ
    0.49
    یاں
    0.48
     עם
    0.48
     فِي
    0.48
    Activations Density 0.004%

    No Known Activations