© 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. 34-GEMMASCOPE-RES-131K
    7. 59414
    Prev
    Next
    INDEX
    Explanations

    control Name, device, or strategy

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

    The neuron fires on occurrences of the token “control” (e.g. the word “Control” in code or text).

    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
    '
    -1.41
    d
    -0.97
    Hola
    -0.96
    b
    -0.96
    entrer
    -0.95
    はな
    -0.95
    Trips
    -0.93
     フラ
    -0.91
    Compiled
    -0.91
    もら
    -0.90
    POSITIVE LOGITS
    ateral
    1.70
    lably
    1.54
    
    1.33
    leur
    1.29
    lable
    1.28
    la
    1.24
    鈑
    1.23
    ++)
    1.22
    lables
    1.18
    controls
    1.16
    Activations Density 0.058%

    No Known Activations