© 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. 22-GEMMASCOPE-RES-131K
    7. 66728
    Prev
    Next
    INDEX
    Explanations

    thus, therefore, hence

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

    The neuron detects numeric tokens—digits or number strings (including integers and decimals) representing quantitative values.

    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
    __*/
    -1.19
     ráp
    -1.16
     cardiaque
    -1.16
     deportivas
    -1.15
    #}
    -1.14
    Nhưng
    -1.09
     allerede
    -1.09
    性の
    -1.07
     kommune
    -1.07
    Địa
    -1.06
    POSITIVE LOGITS
     they
    1.58
     thus
    1.36
     These
    1.29
     therefore
    1.29
     these
    1.27
    They
    1.26
     this
    1.24
     thereby
    1.23
     are
    1.22
     hence
    1.20
    Activations Density 0.100%

    No Known Activations