© 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. 154372
    Prev
    Next
    INDEX
    Explanations

    determiners followed by adjectives

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

    Alternative Theories

    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
    真实
    0.48
    Internet
    0.46
    Micro
    0.46
    从
    0.46
    нуть
    0.46
    ık
    0.46
    许
    0.46
    我们
    0.46
    首页
    0.46
    Nothing
    0.45
    POSITIVE LOGITS
     vod
    0.47
     會
    0.47
     disadvant
    0.46
     イラスト
    0.46
     dipende
    0.45
     tunic
    0.44
     ktoré
    0.44
     poveć
    0.44
     metais
    0.44
     recientemente
    0.43
    Activations Density 0.002%

    No Known Activations