© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44974
    Prev
    Next
    INDEX
    Explanations

    temporal markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     are
    -2.06
     a
    -1.98
     if
    -1.85
     one
    -1.82
     might
    -1.76
     although
    -1.70
     allow
    -1.70
     ensure
    -1.68
     will
    -1.67
     provide
    -1.65
    POSITIVE LOGITS
    </h2>
    1.66
     universitaria
    1.63
     таких
    1.63
     diesen
    1.59
     diesem
    1.58
     любого
    1.58
    [?]
    1.57
    嵓
    1.52
    :--
    1.51
     lorsqu
    1.48
    Activations Density 0.095%

    No Known Activations