© 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. 47242
    Prev
    Next
    INDEX
    Explanations

    purchases and discounts

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

    HTML, SEO, content counts

    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
    催
    0.49
     посвящён
    0.47
    므
    0.46
    powiedz
    0.46
    ności
    0.45
    埒
    0.45
    <unused1921>
    0.45
    争议
    0.44
     посвящен
    0.44
     մ
    0.44
    POSITIVE LOGITS
     blending
    0.52
     blended
    0.52
     journaling
    0.46
     leaning
    0.44
     teamwork
    0.44
     resiliency
    0.43
     posting
    0.42
     distracted
    0.42
     juniors
    0.42
     len
    0.41
    Activations Density 0.000%

    No Known Activations