© 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. 253931
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    пе
    0.52
    idimensional
    0.49
    ㎥
    0.46
     tabled
    0.46
     сильно
    0.45
    を選
    0.44
     Насе
    0.44
     религи
    0.44
    нике
    0.43
     指輪
    0.43
    POSITIVE LOGITS
    sen
    0.44
    Arquivo
    0.44
    บ
    0.43
    Miscellaneous
    0.43
    Certificate
    0.43
     informatie
    0.43
    SEN
    0.42
    ตอนนี้
    0.42
    ع
    0.42
    ا
    0.42
    Activations Density 0.000%

    No Known Activations