© 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. 181099
    Prev
    Next
    INDEX
    Explanations

    file manipulation and sharing

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

    Mark duplicates, true nature, working, percentage, win, endpoints

    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
     vincul
    0.46
    {}
    0.46
     shelf
    0.45
    ҥ
    0.45
     softened
    0.45
     softening
    0.44
    мага
    0.43
     corresponden
    0.43
     {}
    0.43
    льное
    0.43
    POSITIVE LOGITS
     শন
    0.47
    പ്പറ
    0.47
    ennzeichnet
    0.47
    et
    0.47
     சிகிச்ச
    0.47
     ரி
    0.46
    teni
    0.46
    naie
    0.46
    jeno
    0.45
    tti
    0.44
    Activations Density 0.000%

    No Known Activations