© 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. 95771
    Prev
    Next
    INDEX
    Explanations

    age in weeks and months

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

    The neuron fires on numeric tokens and measurement values (e.g., ages, quantities, and statistical figures).

    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
    
    -1.31
     заметил
    -1.27
     thoſe
    -1.27
    龛
    -1.16
     ſome
    -1.15
     créations
    -1.14
    -1.14
    creates
    -1.13
    好みの
    -1.13
     haline
    -1.11
    POSITIVE LOGITS
     October
    1.48
    readFileSync
    1.41
     until
    1.41
     September
    1.38
     škole
    1.38
     because
    1.37
     after
    1.36
     July
    1.35
    𝗼
    1.34
     their
    1.33
    Activations Density 0.093%
    No Known Activations