© 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. 236226
    Prev
    Next
    INDEX
    Explanations

    Clerk queries, age, choice, farmer

    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
    ਕ
    0.50
     Unknown
    0.43
     Receptor
    0.43
    ০
    0.43
    এই
    0.43
     antioxid
    0.43
     complejo
    0.42
     teie
    0.41
    ক্লো
    0.41
     undamaged
    0.41
    POSITIVE LOGITS
    Requests
    0.47
    Burst
    0.47
     два
    0.46
     为
    0.46
     المسا
    0.45
     ዕ
    0.44
    ့်
    0.44
     المنا
    0.43
    UISE
    0.43
     الام
    0.42
    Activations Density 0.000%

    No Known Activations