© 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. 9974
    Prev
    Next
    INDEX
    Explanations

    exceed or surpass a quantity/threshold

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

    beyond a threshold

    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
     findPlayer
    0.47
     udziel
    0.45
     playerName
    0.43
     QText
    0.41
     Extrem
    0.40
    蛐
    0.40
    鹘
    0.40
     participaron
    0.39
    极
    0.39
     ইসলামের
    0.39
    POSITIVE LOGITS
    超過
    1.13
     exceed
    1.12
     exceeds
    1.07
     exceeded
    1.05
     surpass
    1.05
     exceeding
    1.02
     превы
    0.99
    超过
    0.95
     surpassing
    0.93
     surplus
    0.86
    Activations Density 0.116%

    No Known Activations