© 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. 126284
    Prev
    Next
    INDEX
    Explanations

    insurance or without

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

    language/loanwords

    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
    넌
    0.50
    的前
    0.47
     새로운
    0.47
    или
    0.46
     புதிய
    0.46
     teşekkür
    0.46
    にくい
    0.45
     площад
    0.45
     reaf
    0.44
    调
    0.44
    POSITIVE LOGITS
    neither
    0.50
     শুধুমাত্র
    0.48
     neither
    0.48
    store
    0.43
     slechts
    0.43
    insurance
    0.43
    izione
    0.43
    dumps
    0.42
     немає
    0.42
     insured
    0.41
    Activations Density 0.001%

    No Known Activations