© 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. 25755
    Prev
    Next
    INDEX
    Explanations

    submitted dates

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

    The neuron responds to numeric tokens (digits and numbers) in the document, such as dates, page counts, or docket numbers.

    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
    saludos
    -1.00
     опыта
    -0.98
     každého
    -0.96
     первых
    -0.95
     diferença
    -0.95
    咂
    -0.95
     построен
    -0.94
     famosos
    -0.94
    Hmmm
    -0.94
    XP
    -0.93
    POSITIVE LOGITS
     and
    1.34
     his
    1.20
    condido
    1.13
    igree
    1.06
     took
    1.01
     has
    0.99
     ਲਈ
    0.98
     *)&
    0.98
     with
    0.95
    ]&
    0.95
    Activations Density 0.002%

    No Known Activations