© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57994
    Prev
    Next
    INDEX
    Explanations

    scattering amplitudes, experiments, patterns

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

    The neuron strongly activates on the term “scattering,” flagging mentions of scattering phenomena.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
    It
    -3.13
    最初の
    -2.97
    There
    -2.95
    The
    -2.92
    }$
    -2.91
    As
    -2.88
    Although
    -2.86
    釹
    -2.86
    躋
    -2.86
    𐐪
    -2.84
    POSITIVE LOGITS
     berühm
    3.28
     meestal
    3.27
     solches
    3.05
    </em>
    3.03
     $
    2.98
     genellikle
    2.84
    ↵
    2.83
     ehemal
    2.80
     yaklaşık
    2.75
     */
    2.67
    Activations Density 0.005%

    No Known Activations