© 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. 112701
    Prev
    Next
    INDEX
    Explanations

    bioscience and physics

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

    excess, space, holds, suffers, Bud

    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
    w
    0.66
    ve
    0.64
    rt
    0.64
    rate
    0.62
    tt
    0.61
    a
    0.61
    ct
    0.59
    b
    0.59
    ut
    0.59
    o
    0.59
    POSITIVE LOGITS
     轻
    0.57
     subunits
    0.52
     recto
    0.51
     ferries
    0.50
     psicología
    0.50
     subunit
    0.49
    PopMatrix
    0.48
    ุงเทพ
    0.48
     LMFBR
    0.47
    绻
    0.47
    Activations Density 0.000%

    No Known Activations