© 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. 86806
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and compounds

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

    numerical values in scientific and technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens (digit sequences), i.e. it detects numbers in the text.

    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
    genie
    -0.82
     usarlo
    -0.77
     userID
    -0.73
     microondas
    -0.71
     externos
    -0.70
     المد
    -0.70
    ganya
    -0.68
    Ӱ
    -0.68
    CCESS
    -0.68
     setStatus
    -0.68
    POSITIVE LOGITS
    Pierre
    0.84
    ioka
    0.83
    Minn
    0.76
    弾
    0.74
    নি
    0.73
     duc
    0.73
    ">>
    0.72
     ester
    0.72
     Anpass
    0.72
     cilindro
    0.71
    Activations Density 0.001%

    No Known Activations