© 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. 68543
    Prev
    Next
    INDEX
    Explanations

    engine account acquisition

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

    list of foreign language 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
    w
    0.66
    d
    0.62
    q
    0.57
    é
    0.57
    ig
    0.57
    ie
    0.55
    im
    0.54
    hos
    0.52
    x
    0.52
    erta
    0.51
    POSITIVE LOGITS
     Шрифт
    0.60
     componentWill
    0.55
     المؤلف
    0.54
     Полу
    0.52
     Необходимо
    0.52
     Sección
    0.51
     Comunidad
    0.50
     Bước
    0.50
     adquisición
    0.50
     strListName
    0.50
    Activations Density 0.000%

    No Known Activations