© 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. 73320
    Prev
    Next
    INDEX
    Explanations

    late names or estate of names

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

    This neuron activates on numeric tokens—e.g. years, ages, and other number-like values—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
    
    -1.27
    
    -1.23
     patienter
    -1.18
    ïe
    -1.17
     grossesse
    -1.13
     grotte
    -1.11
    ĺ
    -1.08
    🏨
    -1.08
    
    -1.06
     tamaños
    -1.05
    POSITIVE LOGITS
     as
    1.33
     three
    1.20
     so
    1.19
     like
    1.15
     with
    1.14
     four
    1.13
     where
    1.11
     great
    1.10
     similar
    1.07
     from
    1.06
    Activations Density 0.002%

    No Known Activations