© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75326
    Prev
    Next
    INDEX
    Explanations

    those [description]

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

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

    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
     what
    -1.68
    ......”
    -1.51
     الجديدة
    -1.44
     assai
    -1.43
    футболка
    -1.35
    勠
    -1.35
    🤙
    -1.35
    枼
    -1.34
    YNAMICS
    -1.33
    也
    -1.32
    POSITIVE LOGITS
    </b>
    1.66
    magnes
    1.52
     ]);
    1.49
     tendrán
    1.48
     to
    1.46
     foods
    1.45
     from
    1.42
     Tatsache
    1.41
     którym
    1.41
    иболее
    1.39
    Activations Density 0.022%

    No Known Activations