© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34468
    Prev
    Next
    INDEX
    Explanations

    width and spacing

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

    The neuron fires primarily on numeric tokens—i.e. numbers or measurements—embedded 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
    Ayrıca
    -1.40
    メルカリ
    -1.34
    Kleur
    -1.33
    Locatie
    -1.29
    licable
    -1.28
    Algemeen
    -1.26
    zdroj
    -1.25
    Lietu
    -1.23
    OBJETIVOS
    -1.21
    ləş
    -1.21
    POSITIVE LOGITS
     if
    1.50
     for
    1.13
    ὴν
    1.11
     any
    1.05
    无
    0.99
    非
    0.99
     before
    0.99
     Even
    0.96
    】:
    0.96
     вижу
    0.95
    Activations Density 0.005%

    No Known Activations