© 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. 157766
    Prev
    Next
    INDEX
    Explanations

    restaurant chains choose

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

    object detection aims to organ damage

    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
    <b>
    0.49
    ↵↵
    0.46
    協力
    0.45
    import
    0.44
    <
    0.44
    줘
    0.44
     Fl
    0.43
    提到
    0.42
    竹
    0.41
    xml
    0.41
    POSITIVE LOGITS
    ableConcept
    0.54
    sqcup
    0.52
    EndZ
    0.52
     መድሃኒ
    0.50
     സമീപ
    0.49
     സർക്കാർ
    0.49
    UTRON
    0.49
     랜
    0.49
     軍
    0.49
     પસંદ
    0.48
    Activations Density 0.001%

    No Known Activations