© 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. 95350
    Prev
    Next
    INDEX
    Explanations

    numerical questions and assessments

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

    The neuron fires on individual numeric digit tokens (i.e. single‐digit 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
     Desember
    -1.29
     flotte
    -1.20
     reise
    -1.16
     Februari
    -1.13
     Republik
    -1.11
     his
    -1.11
    ㅎ
    -1.11
     amerik
    -1.10
     alkoh
    -1.09
     annen
    -1.09
    POSITIVE LOGITS
    𓈒
    1.14
     conferma
    1.10
    Mace
    1.06
     perceptual
    1.06
     приводит
    1.05
    нося
    1.04
     empuj
    1.03
     сообщил
    1.03
     culoare
    1.02
    亵
    1.02
    Activations Density 0.000%

    No Known Activations