© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72331
    Prev
    Next
    INDEX
    Explanations

    popular searches

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

    The neuron is looking for numerical tokens (digits or 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
     OGSÅ
    -2.06
     streamlined
    -2.03
     There
    -1.73
     tailored
    -1.68
    Shortly
    -1.65
     longstanding
    -1.65
     terlaris
    -1.63
    いかがでしたか
    -1.62
    bluza
    -1.61
    骘
    -1.61
    POSITIVE LOGITS
    u
    2.42
     REALLY
    2.31
     amazingly
    2.16
    te
    2.13
    消失了
    2.09
    en
    2.06
     absurd
    2.02
    </b>
    2.00
     the
    1.95
     VERY
    1.93
    Activations Density 0.007%

    No Known Activations