© 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. 136678
    Prev
    Next
    INDEX
    Explanations

    activities and related concepts

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

    simpleinstructionsnoiseclassics

    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
     ores
    0.44
     USGS
    0.42
     ذ
    0.40
     ಪರಿ
    0.40
     FTC
    0.40
     rods
    0.39
     aftermarket
    0.39
     authorizes
    0.39
    与其他
    0.38
     reactors
    0.38
    POSITIVE LOGITS
     گھر
    0.57
     घर
    0.57
     повседнев
    0.56
     quotidien
    0.50
     ઘર
    0.48
    🎹
    0.47
    日常
    0.47
    Scottish
    0.46
     त्यांनी
    0.46
    Simple
    0.46
    Activations Density 0.001%

    No Known Activations