© 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. 9676
    Prev
    Next
    INDEX
    Explanations

    quantities of people

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

    The neuron flags numeric expressions that specify group size or occupancy capacity (e.g. “sleeps 6,” “for 4 persons,” “accommodate up to six people”).

    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
    -1.63
     to
    -1.48
     will
    -1.45
     new
    -1.22
     it
    -1.21
     prevent
    -1.20
     time
    -1.20
     j
    -1.19
     on
    -1.18
     m
    -1.17
    POSITIVE LOGITS
     family
    1.45
    
    1.43
     kaksi
    1.43
     célèbres
    1.34
    Familien
    1.30
     akár
    1.29
     dátum
    1.28
    𓆏
    1.27
     stratég
    1.27
     braços
    1.26
    Activations Density 0.021%

    No Known Activations