© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 13558
    Prev
    Next
    INDEX
    Explanations

    Balón de Oro, three Reasons, Section 1

    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_16k_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
    และความ
    1.59
     và
    1.48
     and
    1.47
    。
    1.46
    และ
    1.45
    and
    1.37
    but
    1.35
    ।
    1.32
    vectors
    1.31
    した
    1.30
    POSITIVE LOGITS
     blatantly
    1.60
    შინ
    1.48
     বলিব
    1.43
     strikingly
    1.35
    Agregar
    1.34
    Описание
    1.34
    Наи
    1.34
    OTC
    1.30
     oddly
    1.27
    Eo
    1.27
    Activations Density 0.029%

    No Known Activations