© 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. 79355
    Prev
    Next
    INDEX
    Explanations

    USB charge ports interfaces

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

    USB connection or charging

    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
    करणा
    0.55
     बढ़ोतरी
    0.53
    윳
    0.51
     определения
    0.49
    ر
    0.49
    மொ
    0.47
    ቛ
    0.47
    চ
    0.47
    镙
    0.47
    疡
    0.46
    POSITIVE LOGITS
    ía
    0.56
     flock
    0.51
     inflict
    0.49
     padre
    0.47
    ia
    0.47
     widen
    0.46
     came
    0.45
    al
    0.45
    ial
    0.45
     shrink
    0.45
    Activations Density 0.012%

    No Known Activations