© 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. 155425
    Prev
    Next
    INDEX
    Explanations

    after text followed by dates

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

    colors and their meanings

    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
     ferme
    0.44
     réponse
    0.43
     retail
    0.43
    Robert
    0.40
    Reference
    0.40
     odpowiedzi
    0.40
     schizophren
    0.40
    て
    0.39
    쫙
    0.39
     demain
    0.39
    POSITIVE LOGITS
    钨
    0.52
     উত্তম
    0.49
     Stunden
    0.45
     видов
    0.44
     ব্যাপক
    0.43
     Об
    0.43
     बोनस
    0.42
     टॉपिक्स
    0.42
     결방
    0.42
     لديها
    0.42
    Activations Density 0.003%

    No Known Activations