© 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. 223499
    Prev
    Next
    INDEX
    Explanations

    century classroom

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

    cloud desktops, bloodstains, verified merchants

    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
    zeigt
    0.52
    ૯
    0.52
     gleichen
    0.50
    pricht
    0.50
     els
    0.50
     anzeigen
    0.49
    anzi
    0.49
     essi
    0.49
     oberen
    0.48
    즌
    0.48
    POSITIVE LOGITS
    ’
    0.55
     pressed
    0.48
     पत्थर
    0.45
    变成了
    0.44
    Kayak
    0.44
    C
    0.43
    保护
    0.43
    一种
    0.42
     Mining
    0.42
    叩
    0.42
    Activations Density 0.001%

    No Known Activations