© 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. 73426
    Prev
    Next
    INDEX
    Explanations

    Ohio and KA

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

    This neuron detects the numeric‐hyphen sequences used in legal case and docket citations.

    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
     jaren
    -1.31
     poë
    -1.29
     flotte
    -1.27
     planten
    -1.17
    fVar
    -1.16
    {}{}
    -1.13
     durante
    -1.12
     reacties
    -1.09
     dette
    -1.09
    だけの
    -1.09
    POSITIVE LOGITS
     markedly
    1.07
     bemerkt
    1.02
     when
    1.02
     befür
    1.01
     nahezu
    1.00
    abbaye
    1.00
    associazione
    0.99
    Виды
    0.96
     brugt
    0.95
     non
    0.95
    Activations Density 0.082%

    No Known Activations