© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83404
    Prev
    Next
    INDEX
    Explanations

    floor lamp

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

    foreign language or segmented words

    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
     prescription
    0.48
     Prescription
    0.48
    毕竟
    0.47
    는
    0.46
    Government
    0.45
     consecutive
    0.43
    的问题
    0.42
    过于
    0.42
    ؛
    0.41
     zwią
    0.41
    POSITIVE LOGITS
     ditu
    0.48
    ́c
    0.47
     書い
    0.47
    رير
    0.47
    pedido
    0.47
    illas
    0.46
    phdr
    0.46
    ッカー
    0.45
    ecido
    0.45
    etet
    0.45
    Activations Density 0.001%

    No Known Activations