© 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. 10-GEMMASCOPE-RES-131K
    7. 19941
    Prev
    Next
    INDEX
    Explanations

    quantitative image reconstruction

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

    The neuron selectively fires on the “>” (greater‐than/angle‐bracket) character.

    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
    '
    -2.73
     There
    -2.31
    geführt
    -2.05
     ähnliche
    -2.05
    geleitet
    -1.93
     další
    -1.86
    летка
    -1.85
    uscany
    -1.84
    .
    -1.84
    ',
    -1.83
    POSITIVE LOGITS
    s
    1.95
    目的是
    1.85
     первым
    1.84
    諼
    1.80
     食器
    1.79
     eminent
    1.78
     unduly
    1.77
     terwijl
    1.73
    ”?
    1.66
     sufri
    1.64
    Activations Density 0.004%

    No Known Activations