© 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. 177430
    Prev
    Next
    INDEX
    Explanations

    non-english numbers / counts

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

    add and search directories

    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
    cityName
    0.46
    aryana
    0.46
    codigo
    0.45
    agama
    0.45
    m
    0.45
    moto
    0.45
    arro
    0.45
     actuation
    0.45
     remittance
    0.45
    andro
    0.44
    POSITIVE LOGITS
     totiž
    0.48
    以外
    0.47
     ሁለት
    0.44
    分别是
    0.44
    欱
    0.44
     இரண்டு
    0.43
    分别为
    0.43
    槑
    0.43
    ర్జాతీయ
    0.42
     дві
    0.42
    Activations Density 0.010%

    No Known Activations