© 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. 203885
    Prev
    Next
    INDEX
    Explanations

    the end of a sentence or clause

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

    special characters and specific terms

    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
    alya
    0.60
     दगडा
    0.52
     எட்டு
    0.50
     यासाठी
    0.50
    𝙧
    0.50
     vậy
    0.49
     এইভাবে
    0.48
     यामुळे
    0.48
     نزد
    0.47
    ओं
    0.47
    POSITIVE LOGITS
     exaggeration
    0.52
     on
    0.50
     config
    0.48
     Tr
    0.48
     exager
    0.47
     epsilon
    0.46
     $
    0.45
    Tr
    0.45
    ిన
    0.44
       
    0.44
    Activations Density 0.002%

    No Known Activations