© 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. 39790
    Prev
    Next
    INDEX
    Explanations

    p-values and comparisons

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

    The neuron selectively picks up on numerical statistical measures (e.g. reported p-values and related significance statistics).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     who
    -1.98
     incrí
    -1.71
     kenal
    -1.68
     menyen
    -1.64
     cerdas
    -1.57
     laku
    -1.57
     maska
    -1.56
    
    -1.53
     faktor
    -1.52
     flotte
    -1.52
    POSITIVE LOGITS
    "
    1.99
    er
    1.77
    )
    1.69
     L
    1.65
    </h2>
    1.54
     "
    1.47
     
    1.42
    -
    1.41
    ">
    1.41
    ..
    1.37
    Activations Density 0.041%

    No Known Activations