© 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. 234839
    Prev
    Next
    INDEX
    Explanations

    other people groups

    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
     wilfully
    0.46
    ↵↵↵↵
    0.43
     in
    0.42
     tumour
    0.42
    ੱਖ
    0.42
    ：（
    0.42
    avourable
    0.42
    ми
    0.41
     metr
    0.41
    ю
    0.41
    POSITIVE LOGITS
     थोड़ा
    0.48
    Đi
    0.48
    お金
    0.48
     बनाम
    0.47
     এসব
    0.47
     acerca
    0.47
     camaraderie
    0.46
     хозя
    0.46
    招生
    0.46
     lidí
    0.46
    Activations Density 0.000%

    No Known Activations