© 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. 228840
    Prev
    Next
    INDEX
    Explanations

    in + context

    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
     versus
    0.54
     wobec
    0.50
    対
    0.50
     đối
    0.48
     against
    0.48
     против
    0.48
     Gegner
    0.48
     Gastgeber
    0.48
     बनाम
    0.47
     gegen
    0.46
    POSITIVE LOGITS
    FuncName
    0.44
    prepend
    0.41
    で購入
    0.41
    ynku
    0.40
     prune
    0.40
    笫
    0.39
    ertime
    0.39
    ായിരുന്നു
    0.39
    一一
    0.38
     prehistoric
    0.38
    Activations Density 0.042%

    No Known Activations