© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8661
    Prev
    Next
    INDEX
    Explanations

    numbers and superlatives

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

    hover, law, cost related terms

    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
     gamanam
    0.23
    ’
    0.22
     attham
    0.21
    rizio
    0.21
    mara
    0.21
    4
    0.21
    Davidson
    0.20
    Kat
    0.20
    angelo
    0.20
     adhipp
    0.20
    POSITIVE LOGITS
     Regex
    0.25
     Sparse
    0.24
     piecewise
    0.23
    两个
    0.23
     ObjectMapper
    0.22
    槑
    0.22
     Airplane
    0.22
     SizedBox
    0.22
     Polynomial
    0.22
     Iterable
    0.21
    Activations Density 0.546%

    No Known Activations