© 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. 65221
    Prev
    Next
    INDEX
    Explanations

    directory, shapes, range, flooded, broccoli

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

    why, brine, alcohol, explanations

    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
    مع
    0.50
    MLA
    0.49
    มากกว่า
    0.49
    Acceler
    0.47
    Larg
    0.47
    点
    0.46
    Symptoms
    0.46
    Лі
    0.45
    Ві
    0.45
    سم
    0.44
    POSITIVE LOGITS
    ᱑
    0.52
    isLoading
    0.48
    ısını
    0.48
    exports
    0.48
     настроение
    0.48
     shouldn
    0.48
     życie
    0.47
     nus
    0.47
    otransferase
    0.47
     निपटने
    0.46
    Activations Density 0.000%

    No Known Activations