© 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. 47517
    Prev
    Next
    INDEX
    Explanations

    product parts or abstract concepts

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

    Numbers and their relationships

    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
    Closeup
    0.50
    ).^
    0.46
     قیامت
    0.46
     قوم
    0.45
    헷
    0.45
    😂😂
    0.44
    🠀
    0.43
    alike
    0.43
     ایل
    0.43
    🅔
    0.43
    POSITIVE LOGITS
     classmates
    0.50
     cancers
    0.49
     option
    0.46
     efficiency
    0.43
     successes
    0.43
     efficiencies
    0.43
     supply
    0.42
     obligation
    0.42
     increases
    0.42
     is
    0.42
    Activations Density 0.000%

    No Known Activations