© 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. 175096
    Prev
    Next
    INDEX
    Explanations

    year why find yard sign up

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

    city names, countries, officer roles

    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
    k
    0.59
    ९
    0.53
    WARNING
    0.52
    бля
    0.46
    دی
    0.46
    ശ
    0.46
    warning
    0.46
    WILL
    0.45
    kons
    0.45
    동
    0.45
    POSITIVE LOGITS
    igui
    0.56
    duğ
    0.52
     soup
    0.49
     soups
    0.49
     மாற்றம்
    0.49
     nier
    0.48
     erfolgt
    0.47
    oer
    0.47
     oficiais
    0.46
     perfumes
    0.46
    Activations Density 0.000%

    No Known Activations