© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2524
    Prev
    Next
    INDEX
    Explanations

    trades, hotel, train

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     내용은
    1.81
     내용
    1.68
     내용을
    1.64
    Raquete
    1.63
     strListName
    1.62
     작성
    1.62
    ){}^
    1.62
    )^{*}
    1.60
    CORDS
    1.59
     গুলোতে
    1.58
    POSITIVE LOGITS
    ron
    1.22
    ni
    1.06
    hen
    0.97
    opter
    0.97
    initializer
    0.92
    ↵↵↵
    0.88
    domain
    0.85
    think
    0.85
    rv
    0.84
    izem
    0.84
    Activations Density 0.000%

    No Known Activations