© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38476
    Prev
    Next
    INDEX
    Explanations

    proper nouns and scientific terms

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

    The neuron primarily detects numeric tokens (e.g., standalone numbers and numeric measurements).

    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
     in
    -1.68
     by
    -1.66
     on
    -1.62
     when
    -1.58
     with
    -1.55
     that
    -1.47
     any
    -1.47
    !!!!!
    -1.46
     so
    -1.45
     their
    -1.43
    POSITIVE LOGITS
     horrid
    1.67
    没办法
    1.27
     famed
    1.27
     horrible
    1.23
     dreadful
    1.22
     ridiculously
    1.20
     horrifying
    1.20
    usually
    1.20
     splendid
    1.20
     exceedingly
    1.19
    Activations Density 0.073%

    No Known Activations