© 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. 34-GEMMASCOPE-RES-131K
    7. 54021
    Prev
    Next
    INDEX
    Explanations

    reach and extend

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

    The neuron fires strongly on commercial or promotional ad copy, i.e. marketing language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    levé
    -0.92
     marginTop
    -0.86
     Gogh
    -0.82
    runApp
    -0.80
    ąpi
    -0.79
    ihnachten
    -0.79
    ่วม
    -0.77
    "\\
    -0.75
    mpty
    -0.73
    onné
    -0.73
    POSITIVE LOGITS
     reach
    4.16
    reach
    3.16
     reaches
    3.11
     reaching
    3.08
    Reach
    3.06
     Reach
    2.92
     reached
    2.64
    Reaching
    2.63
    reaching
    2.59
     REACH
    2.44
    Activations Density 0.084%

    No Known Activations