© 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. 22-GEMMASCOPE-RES-131K
    7. 129402
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric monetary amounts (especially US dollar values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    US currency amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     in
    -2.44
     with
    -2.16
     on
    -2.02
     at
    -1.87
     that
    -1.70
     because
    -1.68
    !!!!!
    -1.62
     after
    -1.60
    !!!!
    -1.55
    …！
    -1.55
    POSITIVE LOGITS
     provoquer
    1.87
     hinders
    1.81
     hermosos
    1.76
     astounding
    1.70
     gigantic
    1.70
     verdaderos
    1.62
     indescri
    1.59
     muelle
    1.59
    ことも
    1.58
     deliciously
    1.58
    Activations Density 0.004%

    No Known Activations