© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78300
    Prev
    Next
    INDEX
    Explanations

    locally simultaneous

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

    The neuron fires on pure numeric tokens (digit sequences).

    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
     welcoming
    -0.79
    ähren
    -0.76
     uhr
    -0.75
    会社の
    -0.75
    temporal
    -0.73
    european
    -0.73
     garansi
    -0.72
     falls
    -0.71
     webu
    -0.71
     QLabel
    -0.70
    POSITIVE LOGITS
    一致
    0.91
     schema
    0.81
    ouse
    0.77
     peter
    0.76
    ntz
    0.75
    anama
    0.75
    ado
    0.74
    aved
    0.74
     sjuk
    0.73
    扮演
    0.73
    Activations Density 0.000%

    No Known Activations