© 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. 73257
    Prev
    Next
    INDEX
    Explanations

    the following criteria

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

    The neuron activates on numeric measurements or quantities expressed as decimal numbers.

    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
     them
    -1.68
     Then
    -1.64
    ⚊
    -1.55
    随之
    -1.48
    ecciones
    -1.48
     şeyi
    -1.45
    thenReturn
    -1.45
     to
    -1.42
    gsmål
    -1.42
    KommentareTeilen
    -1.41
    POSITIVE LOGITS
    ,
    1.73
    7
    1.64
     rojas
    1.61
    4
    1.52
     男の子
    1.50
    ="
    1.48
    !（
    1.46
    .-
    1.45
    0
    1.45
    5
    1.42
    Activations Density 0.126%

    No Known Activations