© 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. 50195
    Prev
    Next
    INDEX
    Explanations

    responsibilities and calendars

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

    make schedule it

    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
    به
    0.61
    车
    0.51
    車
    0.50
    ಬ
    0.48
    ज
    0.48
    ب
    0.47
    ج
    0.47
    ए
    0.46
    ف
    0.46
     alkene
    0.46
    POSITIVE LOGITS
     gsi
    0.52
     zásob
    0.46
     zwar
    0.46
     tvar
    0.46
     நினைவுச்சின்ன
    0.46
    ining
    0.46
     ಕಂಚ
    0.45
    entown
    0.45
    ೆಂದು
    0.45
     পাঠ
    0.44
    Activations Density 0.000%

    No Known Activations