© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34528
    Prev
    Next
    INDEX
    Explanations

    import, Web3, diagnostic, neutron

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

    The neuron activates on numeric literal tokens (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_34/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
     Listing
    -0.85
     पुलिस
    -0.84
    Listing
    -0.83
    List
    -0.83
     price
    -0.78
     terke
    -0.77
     Respondent
    -0.77
    Respondent
    -0.77
     listing
    -0.76
     Buy
    -0.73
    POSITIVE LOGITS
    CLAIM
    0.90
     cla
    0.90
    nyard
    0.86
    ΐ
    0.84
     checkpoints
    0.82
     nén
    0.81
    chaleco
    0.80
     cresce
    0.79
    Alamat
    0.79
    paigns
    0.78
    Activations Density 0.000%

    No Known Activations