© 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. 174985
    Prev
    Next
    INDEX
    Explanations

    Bluetooth audio devices

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

    Observe Sprint

    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
    Введите
    0.57
    Após
    0.55
    Э
    0.55
    Раз
    0.54
    Estas
    0.54
    Вот
    0.54
    Estos
    0.53
    醗
    0.53
    Datos
    0.52
    Temporary
    0.51
    POSITIVE LOGITS
    nia
    0.57
    ni
    0.56
    arnas
    0.48
    ice
    0.48
    ata
    0.47
    arna
    0.47
    leyici
    0.46
    rie
    0.46
     Indic
    0.45
    na
    0.45
    Activations Density 0.003%

    No Known Activations