© 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. 137935
    Prev
    Next
    INDEX
    Explanations

    sequences followed by nouns

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

    always most often straightforward

    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
    ху
    0.50
    長
    0.48
    му
    0.47
    оти
    0.47
    бно
    0.47
    아
    0.47
    素
    0.47
    ви
    0.46
    ார
    0.46
    ана
    0.46
    POSITIVE LOGITS
    idać
    0.53
     معناها
    0.48
     끝나
    0.48
     답변
    0.46
     معنى
    0.46
     مد
    0.45
     قلت
    0.45
     의미
    0.45
    dicts
    0.44
    തിന്റെ
    0.44
    Activations Density 0.001%

    No Known Activations