© 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. 168522
    Prev
    Next
    INDEX
    Explanations

    production or inspection

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

    giving suggestions

    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
     гене
    0.53
     österreich
    0.47
     Jayne
    0.47
     Mercedes
    0.46
     ép
    0.46
     núcle
    0.45
     Disney
    0.45
    韪
    0.44
     WordPress
    0.44
     macOS
    0.44
    POSITIVE LOGITS
    maßen
    0.48
     ಗೆ
    0.46
    ńst
    0.44
    NORMAL
    0.43
    salmon
    0.41
     ਨਾਲ
    0.40
    koe
    0.40
    Kuota
    0.40
    scratch
    0.40
    ProductRunnable
    0.40
    Activations Density 0.000%

    No Known Activations