© 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. 237931
    Prev
    Next
    INDEX
    Explanations

    sequential punctuation or word endings

    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
    خیص
    0.48
     похо
    0.44
    ряду
    0.43
     ‪
    0.42
    мо
    0.41
     claras
    0.41
    мени
    0.41
    었다
    0.41
     Marx
    0.41
    esti
    0.40
    POSITIVE LOGITS
     inflicting
    0.50
     acknowledges
    0.49
    Rent
    0.48
     ermöglicht
    0.48
     करण्यासाठी
    0.48
    ଗ
    0.47
     profitieren
    0.47
    <unused536>
    0.47
     monotonically
    0.46
    Smoothing
    0.46
    Activations Density 0.000%

    No Known Activations