© 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. 105671
    Prev
    Next
    INDEX
    Explanations

    string beans

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

    pain or injury relief

    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
    ilizar
    0.48
    টিভ
    0.48
    كما
    0.47
    ictionnaire
    0.47
    ే
    0.46
    ील
    0.46
     مك
    0.45
     zodat
    0.45
    ικη
    0.45
    ómago
    0.45
    POSITIVE LOGITS
    */
    0.48
     המס
    0.45
    Trước
    0.41
    Shroud
    0.41
     run
    0.40
     runtime
    0.40
     امریکا
    0.40
    addContainer
    0.39
     cleanse
    0.39
     opposed
    0.39
    Activations Density 0.001%

    No Known Activations