© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13251
    Prev
    Next
    INDEX
    Explanations

    Lower Salmon River

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

    The neuron is strongly activated by numeric tokens (e.g. page, section, or reference 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
     one
    -1.38
    no
    -1.31
     all
    -1.29
     What
    -1.22
     how
    -1.22
     of
    -1.21
     what
    -1.20
    s
    -1.20
     do
    -1.18
    in
    -1.16
    POSITIVE LOGITS
     pomaga
    1.38
    औ
    1.30
    है
    1.28
     produrre
    1.27
    lifier
    1.27
    fazer
    1.27
     permett
    1.23
     aident
    1.23
    ועל
    1.21
     ayudan
    1.20
    Activations Density 0.002%

    No Known Activations