© 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-16K
    7. 12672
    Prev
    Next
    INDEX
    Explanations

    verb followed by past participle

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

    can be used

    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_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
    ;
    0.57
     in
    0.49
    在
    0.48
    nt
    0.46
    蒹
    0.46
    มีการ
    0.45
    美国
    0.43
    大力
    0.43
    ผล
    0.42
    ن
    0.41
    POSITIVE LOGITS
     easily
    0.49
    ിക്കാം
    0.48
     burdensome
    0.48
     cualquier
    0.48
     painful
    0.48
    easily
    0.47
     facilmente
    0.47
    yyum
    0.46
     facilement
    0.46
    hungry
    0.45
    Activations Density 0.078%

    No Known Activations