© 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. 39151
    Prev
    Next
    INDEX
    Explanations

    legal documents and specific entities

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

    The neuron is specifically responding to numeric tokens (blocks of digits), i.e. it picks out numbers and ID-style digit sequences in the text.

    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
     Hrvats
    -0.92
     biela
    -0.90
    %;
    -0.84
    userManager
    -0.83
     výrob
    -0.83
    cch
    -0.82
     kommentar
    -0.80
     caliente
    -0.80
     which
    -0.79
    ുന്നു
    -0.79
    POSITIVE LOGITS
     zwölf
    0.93
    Външни
    0.90
     dessen
    0.85
     Theres
    0.85
     khoe
    0.84
    irected
    0.84
     agri
    0.84
    ̓
    0.84
     idyllic
    0.83
    その
    0.82
    Activations Density 0.008%

    No Known Activations