© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    width and height dimensions

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

    The neuron fires on numeric literal tokens (i.e. any standalone numbers).

    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
    ünkü
    -0.84
    się
    -0.82
     puri
    -0.77
     Webcam
    -0.75
    handelt
    -0.75
    dozer
    -0.75
     čtyř
    -0.75
    𝗢
    -0.74
    Noise
    -0.73
    சு
    -0.73
    POSITIVE LOGITS
     width
    1.53
    width
    1.39
     CGSize
    1.14
     Width
    1.08
    height
    1.01
     height
    0.98
    Width
    0.97
    宽度
    0.90
    breite
    0.82
    fusion
    0.78
    Activations Density 0.006%

    No Known Activations