© 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. 10-GEMMASCOPE-RES-131K
    7. 123577
    Prev
    Next
    INDEX
    Explanations

    court case numbers

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

    This neuron detects multi‐digit numeric identifiers (e.g., case numbers or years).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -2.45
     should
    -1.64
     which
    -1.62
     still
    -1.46
     '
    -1.29
     еще
    -1.29
     create
    -1.29
     pueda
    -1.29
     did
    -1.28
     которых
    -1.26
    POSITIVE LOGITS
    
    1.61
    indicated
    1.51
    őtt
    1.46
    眎
    1.42
    Iam
    1.42
    indicates
    1.41
     meisje
    1.41
    allowing
    1.41
    〬
    1.41
    allows
    1.39
    Activations Density 0.056%

    No Known Activations