© 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. 200168
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    words in many languages

    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
    Насе
    0.49
    GetAll
    0.47
    Спа
    0.46
    澳门
    0.45
    זה
    0.45
    ה
    0.45
    梦
    0.45
    ר
    0.44
    ז
    0.43
    Galaxy
    0.41
    POSITIVE LOGITS
     käs
    0.52
    膾
    0.52
     つい
    0.50
     मीनिंग
    0.50
     ܘ
    0.49
     (?,
    0.49
     änd
    0.49
     ਸੀ
    0.49
     moest
    0.49
     mõ
    0.48
    Activations Density 0.001%

    No Known Activations