© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    code structure and numbers

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

    The neuron fires on standalone numeric tokens (i.e. literal numbers).

    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
     daudz
    -1.04
    gerichts
    -1.00
     uhr
    -0.96
    ÍN
    -0.95
    íí
    -0.94
     to
    -0.92
     sarili
    -0.92
    %%%%%%%%%%%%%%%%
    -0.91
    य
    -0.91
     véritable
    -0.90
    POSITIVE LOGITS
    Your
    1.06
    Remember
    1.00
     samochodu
    0.98
    嘍
    0.97
     broek
    0.96
    要不然
    0.95
    孩子们
    0.94
    最後まで
    0.94
    You
    0.94
    Any
    0.94
    Activations Density 0.001%

    No Known Activations