© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 830
    Prev
    Next
    INDEX
    Explanations

    decoration, waterproof, material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     nettement
    0.59
     golongan
    0.58
     phrasing
    0.57
     battled
    0.57
     battling
    0.56
     underscored
    0.55
    $\$
    0.54
    求める
    0.54
     overseen
    0.54
     championed
    0.54
    POSITIVE LOGITS
     ，
    0.69
     Dekor
    0.66
    防水
    0.62
     waterproof
    0.58
     Decorations
    0.58
     microfiber
    0.57
     Decorative
    0.57
    ，
    0.57
     Waterproof
    0.56
     thickened
    0.56
    Activations Density 0.081%

    No Known Activations