© 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. 212611
    Prev
    Next
    INDEX
    Explanations

    common phrases using two words

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

    literal translation

    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
    服務
    0.49
     ادی
    0.48
    𝘥
    0.47
    функ
    0.46
    itettura
    0.46
    สอง
    0.46
    дек
    0.45
    FUNCTION
    0.45
    部門
    0.44
     الخدمات
    0.44
    POSITIVE LOGITS
     Africans
    0.50
     vul
    0.48
     offenders
    0.48
     mycel
    0.48
     culpable
    0.48
     pubescent
    0.48
     google
    0.47
     i
    0.47
     blemishes
    0.46
     spores
    0.46
    Activations Density 0.001%

    No Known Activations