© 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. 13246
    Prev
    Next
    INDEX
    Explanations

    lightweight

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

    smallness and lightness

    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
     invariants
    0.43
    लाब
    0.42
     Thick
    0.42
     sturdy
    0.41
    द्दल
    0.40
     thick
    0.39
    憤
    0.39
    Munic
    0.39
    Buying
    0.38
     ច
    0.38
    POSITIVE LOGITS
     lightweight
    1.21
     lightness
    1.16
     lighter
    1.13
    轻
    1.11
     Lightweight
    1.10
    軽量
    1.05
     lightest
    1.05
    軽い
    1.05
    輕
    1.00
    lighter
    0.98
    Activations Density 0.190%

    No Known Activations