© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190808
    Prev
    Next
    INDEX
    Explanations

    Offshore Technology conference

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

    contrasting natures

    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
     jeżeli
    0.55
    গ্
    0.47
    ндарт
    0.46
    довле
    0.42
    ynı
    0.42
     एडज
    0.42
    ̧
    0.41
    িতে
    0.41
     yapılacak
    0.41
    如果有
    0.40
    POSITIVE LOGITS
     criou
    0.45
     არა
    0.44
     ಉತ್ಪನ್ನ
    0.44
     disallowed
    0.44
    話
    0.44
     palud
    0.44
     otherworldly
    0.43
     avoided
    0.43
     उत्पादों
    0.42
    手指
    0.42
    Activations Density 0.001%

    No Known Activations