© 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. 125085
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    essential

    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
     returnPacket
    0.52
     przen
    0.52
    সূত্র
    0.52
     মুম্ব
    0.52
     ৰ
    0.52
    水の
    0.50
    CMakeFiles
    0.50
    ऑस्ट्रेलिया
    0.50
     conduz
    0.49
    chromosome
    0.49
    POSITIVE LOGITS
    ings
    0.52
    ick
    0.50
    y
    0.50
     Bulgarian
    0.50
    ung
    0.48
    ai
    0.47
     Karak
    0.47
    ab
    0.46
    este
    0.44
    vin
    0.44
    Activations Density 0.000%

    No Known Activations