© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    grammatical connectors

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

    informal interjections and requests

    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
    ஃப்
    0.44
     hinsichtlich
    0.44
     ("
    0.38
    ஃப
    0.36
     உள்ளிட்ட
    0.36
    罹
    0.34
     অন্যান্য
    0.33
     વિવિધ
    0.33
     (!)
    0.32
    的其他
    0.32
    POSITIVE LOGITS
     cuz
    0.53
     কারন
    0.48
     idk
    0.46
     इसको
    0.45
     उसमे
    0.45
     बच्चो
    0.44
     they
    0.44
     THEY
    0.44
     якщо
    0.44
     ።
    0.44
    Activations Density 0.287%

    No Known Activations