© 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. 119242
    Prev
    Next
    INDEX
    Explanations

    circuit court rules

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

    The neuron activates on tokens made up of digits (i.e. numeric 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
     under
    -0.85
    婦
    -0.75
     Detention
    -0.68
    妇
    -0.66
     ideias
    -0.66
    積み
    -0.66
    OLO
    -0.65
    дно
    -0.65
     nasel
    -0.65
     details
    -0.64
    POSITIVE LOGITS
    Vas
    0.81
     Vas
    0.77
    リーズ
    0.70
     VAS
    0.69
    øb
    0.69
    Secondary
    0.68
     subtotal
    0.68
    ᅥ
    0.67
     TSP
    0.66
     FRED
    0.66
    Activations Density 0.058%

    No Known Activations