© 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. 66484
    Prev
    Next
    INDEX
    Explanations

    birth place and date

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

    The neuron flags numeric tokens—especially years and date figures—wherever they appear 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
     kupić
    -1.26
     Bildschirm
    -1.14
     występu
    -1.12
     zobaczyć
    -1.11
     suscripción
    -1.10
     proposé
    -1.07
     uzyskać
    -1.07
     zrobić
    -1.07
     their
    -1.05
    couvrez
    -1.05
    POSITIVE LOGITS
     vitale
    1.19
     rurale
    1.16
     and
    1.16
     with
    1.14
     had
    1.13
     masina
    1.11
     golfe
    1.08
    менты
    1.07
     of
    1.06
    IRECT
    1.06
    Activations Density 0.005%

    No Known Activations