© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8843
    Prev
    Next
    INDEX
    Explanations

    emphasis on specific items

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

    The neuron activates on numeric tokens (numbers) in the document.

    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
     avenir
    -1.82
    \
    -1.76
    𓆏
    -1.74
    .
    -1.71
    蠖
    -1.69
    raisers
    -1.66
     konkret
    -1.66
     salari
    -1.65
     illustre
    -1.65
     gratuite
    -1.64
    POSITIVE LOGITS
    Зно
    1.59
     после
    1.54
     dejar
    1.51
     dañ
    1.51
     There
    1.48
    瑧
    1.45
    ଽ
    1.45
     changes
    1.45
     confronti
    1.45
    ↵
    1.44
    Activations Density 0.026%

    No Known Activations