© 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. 21351
    Prev
    Next
    INDEX
    Explanations

    grammatical noun

    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
    精致
    -1.96
    銩
    -1.77
     ‚
    -1.69
    owany
    -1.64
     ´
    -1.63
    ötzlich
    -1.60
    umumkan
    -1.58
    archiwizowane
    -1.57
     unſ
    -1.55
     rangi
    -1.55
    POSITIVE LOGITS
     this
    2.03
     that
    1.92
     more
    1.83
     if
    1.72
    𐐪
    1.67
     でも
    1.66
     at
    1.51
    伱
    1.51
     those
    1.48
     einzigartigen
    1.48
    Activations Density 0.015%

    No Known Activations