© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207037
    Prev
    Next
    INDEX
    Explanations

    personal payment

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

    creating or describing methods

    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
     blat
    0.46
     CONGRESS
    0.45
     nomenclatura
    0.44
     Monat
    0.42
     काँग्रेस
    0.41
    ἄ
    0.41
    ंदरे
    0.40
    ান্ডার
    0.40
     parfaite
    0.39
     кредит
    0.39
    POSITIVE LOGITS
    สร้าง
    0.49
    วิธีการ
    0.46
    ว
    0.46
    CCO
    0.45
    ]",
    0.44
    it
    0.44
    ք
    0.44
    nę
    0.43
    เขียน
    0.43
    کو
    0.43
    Activations Density 0.002%

    No Known Activations