© 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. 154264
    Prev
    Next
    INDEX
    Explanations

    excelling, cheer, just, responding

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

    endings after punctuation, descriptions

    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
     پیسې
    0.61
     شرطونه
    0.52
     zgod
    0.52
    ١
    0.51
    ጼ
    0.51
     aprende
    0.50
    Сред
    0.47
     Chauhan
    0.47
     डु
    0.47
     sajana
    0.47
    POSITIVE LOGITS
    ilities
    0.52
    giv
    0.52
    io
    0.47
    ников
    0.46
     glTex
    0.46
    ত্রের
    0.46
    iveness
    0.46
     떨어
    0.46
    enia
    0.46
    ő
    0.46
    Activations Density 0.001%

    No Known Activations