© 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. 228083
    Prev
    Next
    INDEX
    Explanations

    phrases and sequences

    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
     suppressing
    0.50
    に関する
    0.50
    ・・・・
    0.50
    appears
    0.49
    ྞ
    0.49
     finer
    0.48
    しまいます
    0.48
     ironic
    0.47
     approximating
    0.47
     denoting
    0.46
    POSITIVE LOGITS
     Palabra
    0.50
     caminho
    0.50
     以及
    0.48
     的
    0.48
     presente
    0.47
     pesc
    0.47
    uszko
    0.47
     الأ
    0.46
     ష
    0.46
     Debido
    0.45
    Activations Density 0.000%

    No Known Activations