© 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. 45122
    Prev
    Next
    INDEX
    Explanations

    speed

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

    The neuron fires on occurrences of the token “fast.”

    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
     We
    -2.27
     pierce
    -2.23
     eliminar
    -2.22
     เรา
    -2.13
     tidak
    -2.09
     หรือ
    -2.05
    芨
    -2.05
    沬
    -2.03
     ating
    -2.00
    钍
    -2.00
    POSITIVE LOGITS
    ing
    3.72
    er
    3.41
    u
    3.02
    ’
    2.64
    ers
    2.61
    說
    2.50
     réfugiés
    2.42
    est
    2.36
     frasi
    2.34
    self
    2.33
    Activations Density 0.007%

    No Known Activations