© 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. 92956
    Prev
    Next
    INDEX
    Explanations

    chlorinated compounds and derivatives

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

    chemical compounds containing chlorine, especially "chloro-" prefixed chemical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on chemical terms containing the “chlor” (chloro-) substring, i.e. chlorine-containing groups or compounds.

    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
    t
    -2.11
    v
    -1.95
     When
    -1.80
     dañ
    -1.77
     wineries
    -1.73
     большин
    -1.69
     Ayrıca
    -1.66
     strange
    -1.66
     heisst
    -1.65
     Both
    -1.63
    POSITIVE LOGITS
     celeste
    1.97
     perla
    1.81
    茕
    1.77
     niya
    1.74
     were
    1.70
     distante
    1.70
     geng
    1.70
     itſelf
    1.66
     PUST
    1.63
    昳
    1.63
    Activations Density 0.040%

    No Known Activations