© 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. 22-GEMMASCOPE-RES-131K
    7. 27899
    Prev
    Next
    INDEX
    Explanations

    transaction confirmations

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

    The neuron strongly activates on numeric tokens (digits and numbers, including decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     espirituales
    -1.33
     religiosos
    -1.13
     vincula
    -1.13
    :
    -1.09
     estren
    -1.09
     filós
    -1.09
     and
    -1.06
    ֠
    -1.04
     помощью
    -1.03
    ֭
    -1.02
    POSITIVE LOGITS
    ֶּ
    1.51
    ֵּ
    1.16
     CLIENT
    1.15
     dégustation
    1.13
     clients
    1.13
     onsdag
    1.13
     zumindest
    1.13
     luminos
    1.13
     sula
    1.13
     cilind
    1.12
    Activations Density 0.003%

    No Known Activations