© 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. 104404
    Prev
    Next
    INDEX
    Explanations

    speaking before "year"

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

    basic information labels

    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
     }^{-
    0.55
    า
    0.54
    ュー
    0.53
    帰り
    0.52
    ো
    0.51
    咊
    0.49
     estimés
    0.49
    垶
    0.49
    nées
    0.48
    zé
    0.48
    POSITIVE LOGITS
    0.53
     Play
    0.52
     Spiel
    0.50
     Symph
    0.49
     Vietnam
    0.48
     formic
    0.48
     Син
    0.46
     Wittgenstein
    0.46
     Being
    0.46
     Com
    0.46
    Activations Density 0.000%

    No Known Activations