© 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. 121919
    Prev
    Next
    INDEX
    Explanations

    historical figures, saints, sources, and others

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

    addressing you or location specific

    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
     wonders
    0.48
    r
    0.48
    0.47
     emigration
    0.47
     miracle
    0.44
    hab
    0.44
    èl
    0.44
    sel
    0.44
    section
    0.43
    D
    0.43
    POSITIVE LOGITS
    BlockUsed
    0.54
    PropertyParam
    0.54
    厙
    0.50
    툐
    0.50
     เด่น
    0.49
     สืบค้นเมื่อ
    0.48
    חים
    0.46
    צים
    0.46
    뗑
    0.46
    日から
    0.46
    Activations Density 0.001%

    No Known Activations