© 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. 37928
    Prev
    Next
    INDEX
    Explanations

    Q questions

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

    The neuron strongly activates on numeric tokens (digits and number‐related symbols).

    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
     женщина
    -0.88
    急に
    -0.83
    rière
    -0.82
    sequently
    -0.78
    帧
    -0.78
    ʹ
    -0.78
     (\<
    -0.77
     ester
    -0.77
    serde
    -0.77
     施工
    -0.75
    POSITIVE LOGITS
     linked
    0.93
     stress
    0.91
     +
    0.89
     overcome
    0.87
     suffer
    0.86
     focused
    0.86
     dice
    0.84
     ignore
    0.81
     marked
    0.81
     stepped
    0.80
    Activations Density 0.010%

    No Known Activations