© 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. 216833
    Prev
    Next
    INDEX
    Explanations

    positive feelings

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

    digits, integers, and comparisons

    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
     olacaktır
    0.58
     yapacağız
    0.52
    娲
    0.46
    سكر
    0.45
    دن
    0.45
     recommandée
    0.45
     encontrará
    0.44
    يرين
    0.44
    سٹم
    0.44
    ដែលអាច
    0.44
    POSITIVE LOGITS
    頗
    0.48
    pleasant
    0.46
     cheerful
    0.43
     cheery
    0.43
     suburban
    0.42
     upbeat
    0.42
     giddy
    0.41
    šk
    0.41
     coolant
    0.41
    excited
    0.41
    Activations Density 0.002%

    No Known Activations