© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11312
    Prev
    Next
    INDEX
    Explanations

    case study descriptions

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

    providing numerical answers

    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_40_width_16k_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
     بأن
    0.44
    Ɖ
    0.41
     Kiara
    0.40
    consumers
    0.39
    kitty
    0.39
     peels
    0.38
    খি
    0.38
     zeros
    0.38
     Peachtree
    0.37
    mySocket
    0.37
    POSITIVE LOGITS
     مقارنه
    0.43
     ничек
    0.42
     begrij
    0.41
    Want
    0.41
    ISTR
    0.40
    Q
    0.40
     Immunol
    0.39
    Understanding
    0.39
     lähe
    0.39
     Understanding
    0.39
    Activations Density 0.002%

    No Known Activations