© 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. 219942
    Prev
    Next
    INDEX
    Explanations

    work and quality

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

    components from house hold appliances

    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
    с
    0.46
    ering
    0.44
    s
    0.43
    edy
    0.43
     আহসান
    0.43
    eds
    0.41
    While
    0.41
    ార్
    0.39
    ensors
    0.39
    ப்புக
    0.39
    POSITIVE LOGITS
     relevancia
    0.66
     resulta
    0.64
     quisquam
    0.57
     destacó
    0.56
     análisis
    0.54
    کن
    0.53
    گیز
    0.52
    >)`](
    0.52
    मिथ
    0.52
     vivió
    0.52
    Activations Density 0.000%

    No Known Activations