© 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. 73043
    Prev
    Next
    INDEX
    Explanations

    conventional varieties

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

    businesses expanding

    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
     ﺍ
    0.52
     いつ
    0.49
     گم
    0.49
     過
    0.48
     추가
    0.47
     언제
    0.47
     اور
    0.46
     さ
    0.46
    NUT
    0.46
     ខ
    0.44
    POSITIVE LOGITS
    द्योगिक
    0.49
     double
    0.48
     testimonials
    0.48
     mansions
    0.47
    loh
    0.47
     двой
    0.45
    EntityFramework
    0.44
     directors
    0.44
     clotting
    0.44
     scholarly
    0.43
    Activations Density 0.001%

    No Known Activations