© 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. 137428
    Prev
    Next
    INDEX
    Explanations

    versatile artists or cheaper price

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

    route manual sequence religion

    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
     بلند
    0.52
     continuamos
    0.48
    抟
    0.48
    Representative
    0.46
     знания
    0.46
    ുമെന്ന്
    0.46
     المملكة
    0.46
     continú
    0.45
     anului
    0.44
     digitalen
    0.44
    POSITIVE LOGITS
     要
    0.46
     caravans
    0.46
     vegetables
    0.45
    paying
    0.45
     自己
    0.45
     automobiles
    0.44
     utilizzare
    0.44
    方式
    0.44
     cheaper
    0.44
     gum
    0.44
    Activations Density 0.001%

    No Known Activations