© 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. 245197
    Prev
    Next
    INDEX
    Explanations

    international trade, emergency, currency

    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
     വനി
    0.50
    高齢
    0.47
    顺利
    0.46
     وط
    0.46
    র
    0.44
     イベント
    0.44
    Dans
    0.44
    ვე
    0.44
     `>=`,
    0.44
     ആരംഭ
    0.44
    POSITIVE LOGITS
    financ
    0.49
     bitumen
    0.48
     payment
    0.46
     Financ
    0.46
     substance
    0.44
     jumper
    0.43
     blatantly
    0.42
     damaged
    0.42
    speak
    0.41
    speaker
    0.41
    Activations Density 0.001%

    No Known Activations