© 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. 77086
    Prev
    Next
    INDEX
    Explanations

    date of, year, tilt, orbit

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

    leap year calculations

    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
     dniu
    0.47
     müm
    0.46
    滝
    0.44
    ্রয়
    0.43
    Leben
    0.43
    Weekday
    0.43
    لی
    0.41
     příst
    0.41
     başka
    0.41
    ി
    0.41
    POSITIVE LOGITS
    ensure
    0.45
     ডিপ
    0.43
    orpions
    0.42
    bed
    0.42
    jni
    0.42
    applicants
    0.42
     правило
    0.41
    chained
    0.41
    applications
    0.40
     ಸರ
    0.40
    Activations Density 0.001%

    No Known Activations