© 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. 39660
    Prev
    Next
    INDEX
    Explanations

    light and its attributes

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

    lighthearted

    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
    0.74
    s
    0.68
    ate
    0.68
    af
    0.65
    л
    0.63
    ap
    0.61
    ारे
    0.61
    akses
    0.61
    ูล
    0.59
    ari
    0.59
    POSITIVE LOGITS
     lighten
    1.07
     light
    1.06
    Light
    1.06
     Light
    0.97
    н
    0.96
    輕
    0.96
     LIGHT
    0.93
     lightest
    0.91
    light
    0.89
     licht
    0.87
    Activations Density 0.075%

    No Known Activations