© 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. 251842
    Prev
    Next
    INDEX
    Explanations

    insurance, clubs, cushions

    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
     Willem
    0.49
    قف
    0.48
    酲
    0.45
    امی
    0.45
    巴巴
    0.44
    极其
    0.44
    Bare
    0.44
    تا
    0.44
    Emily
    0.44
    пита
    0.43
    POSITIVE LOGITS
     మో
    0.49
    ៤
    0.48
    leve
    0.46
     financi
    0.45
     parlour
    0.45
     ४
    0.45
     levando
    0.44
    ipp
    0.44
    lat
    0.44
     telep
    0.44
    Activations Density 0.000%

    No Known Activations