© 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. 250771
    Prev
    Next
    INDEX
    Explanations

    specialized phrases

    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
    '
    0.59
    ↵
    0.59
     Stellen
    0.50
     Barn
    0.46
    Dispatcher
    0.46
     Meng
    0.46
     Daniela
    0.45
     Menon
    0.45
    XmlElement
    0.45
    Mand
    0.44
    POSITIVE LOGITS
     ケ
    0.54
    ny
    0.51
     ପ
    0.50
     vajj
    0.50
    偒
    0.49
    杝
    0.49
    াকেও
    0.48
     আগের
    0.48
    羢
    0.48
     доступ
    0.48
    Activations Density 0.000%

    No Known Activations