© 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. 98400
    Prev
    Next
    INDEX
    Explanations

    explaining words and terms

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

    The neuron primarily detects numeric tokens—especially decimal numbers and related punctuation.

    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
     seçenek
    -1.04
     أجل
    -1.00
     modelleri
    -0.96
    下列
    -0.94
    tvguidetime
    -0.93
    օ
    -0.92
     unul
    -0.92
    Už
    -0.91
     üzer
    -0.91
    dtp
    -0.90
    POSITIVE LOGITS
     in
    1.30
     we
    1.20
     literally
    1.15
    暧
    1.13
     not
    1.09
     used
    1.07
    دد
    1.06
    rían
    1.06
    ֩
    1.04
    <em>
    1.02
    Activations Density 0.012%

    No Known Activations