© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    preamble or question starters

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

    The neuron strongly activates on multi‐digit numeric tokens (e.g. year 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
     péro
    -1.23
     fré
    -1.21
    midler
    -1.16
     tableta
    -1.15
    точка
    -1.14
     domésticos
    -1.13
     viera
    -1.12
     persil
    -1.11
     instala
    -1.09
    projek
    -1.09
    POSITIVE LOGITS
    ara
    1.08
    ay
    1.07
    k
    1.05
     membri
    1.02
    منم
    1.00
     archaeologist
    0.97
    im
    0.97
    et
    0.96
    c
    0.94
     imperialist
    0.93
    Activations Density 0.000%

    No Known Activations