© 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. 241993
    Prev
    Next
    INDEX
    Explanations

    federal laws, families, makeup lessons

    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
    OS
    0.51
    COUNT
    0.46
    DOM
    0.46
    ITAL
    0.45
    SERVICE
    0.44
    3
    0.44
    巷
    0.44
    BR
    0.44
    Britain
    0.44
    2
    0.43
    POSITIVE LOGITS
     kvadrat
    0.48
    ようになって
    0.48
     ló
    0.46
     forskj
    0.46
     साफ
    0.46
     प्रोटीन
    0.45
     Trời
    0.43
     قیمت
    0.43
     युग्
    0.43
     jasno
    0.43
    Activations Density 0.005%

    No Known Activations