© 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. 12096
    Prev
    Next
    INDEX
    Explanations

    sentence terminators and entities

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

    list items, bullet points, dates

    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
     Saltar
    0.71
     Ş
    0.61
     Zweiten
    0.61
     Red
    0.59
     Перейти
    0.58
     İlçesi
    0.55
     F
    0.55
     Messieurs
    0.55
     R
    0.54
     Desenvolvimento
    0.54
    POSITIVE LOGITS
     méxico
    0.95
     barcelona
    0.88
     january
    0.86
     february
    0.84
     thursday
    0.80
     october
    0.78
     españa
    0.77
     australia
    0.76
     saturday
    0.76
     madrid
    0.76
    Activations Density 0.327%

    No Known Activations