© 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. 124797
    Prev
    Next
    INDEX
    Explanations

    multilingual content diversity

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

    inject, level up, AI explode

    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
     کوشش
    0.50
     fondness
    0.47
     попы
    0.47
    ^+,
    0.47
     setState
    0.47
    ಾಪ
    0.47
     plow
    0.46
    하거나
    0.45
    FFEE
    0.45
     വഴി
    0.45
    POSITIVE LOGITS
     अनुच्छेद
    0.48
    osta
    0.47
    ورا
    0.44
     места
    0.43
    لا
    0.43
    न
    0.43
    ابه
    0.43
     traduc
    0.43
    خ
    0.42
     صدر
    0.42
    Activations Density 0.000%

    No Known Activations