© 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. 60773
    Prev
    Next
    INDEX
    Explanations

    IANS

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

    The neuron selectively responds to numeric tokens (numbers or number‐containing strings) 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
    </i>
    -4.00
    </strong>
    -3.33
    </u>
    -2.97
    </h1>
    -2.91
    </h3>
    -2.75
    sweise
    -2.59
    皛
    -2.56
    ла
    -2.45
    釙
    -2.28
    ଝ
    -2.28
    POSITIVE LOGITS
    ྕ
    2.50
     are
    2.45
    逦
    2.31
     支援
    2.23
    时代的
    2.19
    I
    2.16
    濑
    2.16
    на
    2.16
     
    2.14
    at
    2.09
    Activations Density 0.014%

    No Known Activations