© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    ten thousand

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

    if then constraint

    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
     vatten
    0.46
    ൪
    0.45
     flung
    0.44
     roused
    0.44
     chauss
    0.43
    ਾਲ
    0.42
    怎么
    0.42
     ritorno
    0.42
     copertura
    0.41
     arriv
    0.41
    POSITIVE LOGITS
    this
    0.54
    the
    0.52
    pere
    0.50
    p
    0.50
    variable
    0.49
    spi
    0.49
     प्लस
    0.49
    vestre
    0.48
     प्रवासी
    0.48
    facet
    0.48
    Activations Density 0.000%

    No Known Activations