© 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. 210797
    Prev
    Next
    INDEX
    Explanations

    checking options

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

    uncomment

    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
    p
    0.60
     refute
    0.55
     পরিত্যাগ
    0.52
    my
    0.52
     त्याग
    0.52
     dechlor
    0.51
    ai
    0.50
    はお
    0.50
    do
    0.50
    yourself
    0.49
    POSITIVE LOGITS
    ות
    0.64
    ت
    0.62
    ي
    0.60
    يلي
    0.59
    ною
    0.57
    يد
    0.57
    ми
    0.56
    يل
    0.55
    يلا
    0.54
    يون
    0.54
    Activations Density 0.000%

    No Known Activations