© 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. 145581
    Prev
    Next
    INDEX
    Explanations

    systems were, selected or, marked in, consciousness about, Enable single, expand

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

    detailed and descriptive styles

    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
     a
    0.45
     b
    0.45
    ament
    0.42
     instability
    0.42
    連接
    0.40
    شل
    0.39
     lanc
    0.39
     brighter
    0.39
     stripes
    0.38
    祖
    0.38
    POSITIVE LOGITS
     calorías
    0.52
     membahas
    0.49
    𝗺
    0.49
     описание
    0.48
    rugated
    0.48
     обсу
    0.47
    ведений
    0.47
     கடல்
    0.47
     ભર
    0.47
    姮
    0.46
    Activations Density 0.001%

    No Known Activations