© 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. 208639
    Prev
    Next
    INDEX
    Explanations

    do so

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

    spice levels

    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
    深入
    0.47
    푼
    0.46
    接下来
    0.45
    ванович
    0.44
    бор
    0.41
    اموش
    0.40
    CurrentByte
    0.40
    igueur
    0.40
    lesh
    0.40
    بير
    0.40
    POSITIVE LOGITS
    t
    0.60
     eqn
    0.56
     a
    0.52
    s
    0.52
     ECON
    0.51
     frugal
    0.50
    y
    0.50
     Bà
    0.50
    a
    0.50
     PDE
    0.49
    Activations Density 0.000%

    No Known Activations