© 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. 184065
    Prev
    Next
    INDEX
    Explanations

    knowledge leads to

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

    historical narratives and lists

    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
    ']}
    0.56
    নকে
    0.54
    jogador
    0.52
    を発表
    0.51
    ட்ரோ
    0.50
    populations
    0.50
    мом
    0.49
    ாண
    0.49
    страницу
    0.48
    াৰ
    0.48
    POSITIVE LOGITS
     i
    0.52
     beng
    0.50
     Hadoop
    0.49
     siku
    0.49
     Schengen
    0.47
    뿐
    0.46
     remit
    0.46
     tel
    0.46
     brin
    0.46
     cytosol
    0.45
    Activations Density 0.001%

    No Known Activations