© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103901
    Prev
    Next
    INDEX
    Explanations

    agreed to in writing

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

    The neuron strongly responds to numeric tokens—digits, version numbers, and chemical‐formula indices.

    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
     Kwan
    -0.74
    יתי
    -0.73
     コーナー
    -0.73
     identity
    -0.72
    Manually
    -0.68
     garantiert
    -0.67
    tq
    -0.66
     Identities
    -0.66
    sil
    -0.66
     الدولي
    -0.66
    POSITIVE LOGITS
    เอง
    0.70
    traceback
    0.69
    CPI
    0.67
     دریا
    0.67
    +{
    0.66
     moduli
    0.66
     CPI
    0.66
     Lokales
    0.63
     would
    0.63
    óngase
    0.63
    Activations Density 0.070%

    No Known Activations