© 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. 66822
    Prev
    Next
    INDEX
    Explanations

    gouldian, hare, writing task

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

    different types of queries and scenarios

    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
    ƙ
    0.47
     kome
    0.47
    Гу
    0.46
    help
    0.46
    醫
    0.45
    А
    0.43
    institute
    0.42
    rpart
    0.42
    េ
    0.42
    Е
    0.42
    POSITIVE LOGITS
     Frankie
    0.49
     bạn
    0.48
     هنتكلم
    0.47
     이게
    0.44
     बंध
    0.43
    驊
    0.42
    ্কা
    0.42
     Mooney
    0.41
     Freddy
    0.41
     Bagg
    0.41
    Activations Density 0.000%

    No Known Activations