© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70747
    Prev
    Next
    INDEX
    Explanations

    time indicators

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

    This neuron selectively activates on numeric tokens (e.g. digits and multi‐digit 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_22/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
    を行いました
    -2.30
    をしました
    -2.30
    あぁ
    -2.19
    ごめん
    -2.16
    を行います
    -2.14
    もうすぐ
    -2.14
    あー
    -2.11
    の方に
    -2.11
    されていない
    -2.09
    明日は
    -2.08
    POSITIVE LOGITS
    0
    2.27
     to
    2.16
    <bos>
    2.13
    an
    2.08
    </i>
    1.95
    </h1>
    1.80
    </strong>
    1.70
    a
    1.60
    ,’
    1.55
    </sub>
    1.51
    Activations Density 0.009%

    No Known Activations