© 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. 184761
    Prev
    Next
    INDEX
    Explanations

    verified by, keywords=, Tax®

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

    lighthouse keeper

    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
    毆
    0.55
    rž
    0.54
    énie
    0.53
    ন
    0.52
     技術
    0.51
    كثر
    0.50
    Forgery
    0.50
    ਨ
    0.50
    ክ
    0.50
     เพิ่ม
    0.48
    POSITIVE LOGITS
     Roses
    0.49
     soil
    0.47
     soin
    0.46
     roses
    0.45
     toon
    0.44
     seasoning
    0.44
     arriving
    0.43
    soil
    0.42
     mood
    0.42
     apos
    0.42
    Activations Density 0.000%

    No Known Activations