© 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. 500
    Prev
    Next
    INDEX
    Explanations

    Effects of mathematical operations

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

    This neuron fires on the very first token of a new document or major text block (i.e. it detects paragraph/section headers).

    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
     spesies
    -1.10
     necessities
    -1.02
     volant
    -1.01
     servicios
    -0.98
     arras
    -0.98
     flore
    -0.96
    ÚS
    -0.93
     simpto
    -0.93
     comidas
    -0.93
     onPostExecute
    -0.93
    POSITIVE LOGITS
     одновременно
    0.88
     halten
    0.84
     How
    0.82
     confining
    0.80
    tilled
    0.80
     на
    0.79
    の方に
    0.79
     hisz
    0.79
    важа
    0.78
     reichen
    0.78
    Activations Density 0.010%

    No Known Activations