© 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. 34-GEMMASCOPE-RES-131K
    7. 99784
    Prev
    Next
    INDEX
    Explanations

    wedding dress

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

    The neuron fires on numeric characters, especially long multi‐digit sequences (e.g. phone numbers or other numerical strings).

    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
     Stare
    -0.83
     professeurs
    -0.82
    睚
    -0.81
    eby
    -0.80
    ocide
    -0.77
    okes
    -0.76
    guli
    -0.76
     velour
    -0.75
     Bana
    -0.74
    geschenk
    -0.74
    POSITIVE LOGITS
     inflict
    0.80
     /
    0.79
     weten
    0.78
     ті
    0.77
     Wię
    0.73
     NOTE
    0.73
    Collaborative
    0.73
    RuntimeObject
    0.71
     relies
    0.71
    ลด
    0.70
    Activations Density 0.011%

    No Known Activations