© 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. 22-GEMMASCOPE-RES-131K
    7. 129765
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized in detecting numeric tokens or sequences of digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Occupational injury

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     noticeable
    -1.48
    をしました
    -1.46
     three
    -1.30
     There
    -1.29
    総評
    -1.26
    づけ
    -1.23
    おわりに
    -1.23
    corrhi
    -1.21
     horribly
    -1.20
    chaise
    -1.20
    POSITIVE LOGITS
     Dinas
    1.17
     karier
    1.16
     dismal
    1.13
    ent
    1.13
    tian
    1.11
    bers
    1.10
    例えば
    1.10
     technische
    1.09
    zzz
    1.08
    などが
    1.08
    Activations Density 0.015%

    No Known Activations