© 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. 216375
    Prev
    Next
    INDEX
    Explanations

    cases, countless, backdrop, anti, Ride, along, Nor

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

    change, changes, wish, source

    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
    柠
    0.55
    었
    0.51
    했지만
    0.50
    했다
    0.49
     했
    0.49
     했다
    0.47
    렀
    0.46
    зло
    0.45
    bindingFields
    0.45
    했
    0.44
    POSITIVE LOGITS
    ຂ
    0.45
    دد
    0.45
    الس
    0.44
    ابقة
    0.44
    鐳
    0.43
    ्वे
    0.43
    NewGuid
    0.43
    getResponse
    0.43
     déposer
    0.43
    વાર
    0.42
    Activations Density 0.001%

    No Known Activations