© 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. 258893
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Iodine
    0.50
     offices
    0.49
     iodine
    0.46
    )}=
    0.46
    LoginPage
    0.45
     Dezember
    0.45
     Homemade
    0.44
    ➖➖
    0.43
    MainWindow
    0.43
    🅴
    0.42
    POSITIVE LOGITS
    hev
    0.42
     Arroyo
    0.40
    の水
    0.39
    presa
    0.39
    phas
    0.39
    uj
    0.38
    ッサ
    0.38
    衡
    0.38
    の効果
    0.37
     Bots
    0.36
    Activations Density 0.000%

    No Known Activations