© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59443
    Prev
    Next
    INDEX
    Explanations

    key is pressed

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

    The neuron fires on occurrences of the verb “press” in its various forms (pressing, pressed, Pressed, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    {
    -4.50
    z
    -3.52
    u
    -3.34
    m
    -3.31
    er
    -3.13
    acterísticas
    -3.13
     was
    -3.00
    ’?
    -2.78
    x
    -2.66
    r
    -2.64
    POSITIVE LOGITS
    ಞ
    2.66
    灩
    2.56
     aña
    2.53
    好きです
    2.48
    ↵
    2.41
    ･･
    2.39
     variety
    2.39
    鈑
    2.38
     "",
    2.36
    眼下
    2.33
    Activations Density 0.005%

    No Known Activations