© 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. 129305
    Prev
    Next
    INDEX
    Explanations

    programming size units

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

    The neuron is essentially inactive on all inputs shown—it doesn’t reliably detect any specific token pattern.

    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
    ?”
    -3.59
    ”(
    -3.11
    ↵
    -2.95
    ”-
    -2.89
    -”
    -2.66
    :”
    -2.66
    ,”
    -2.64
    ?
    -2.63
    ….”
    -2.58
    ..”
    -2.56
    POSITIVE LOGITS
    是非常
    3.05
    萣
    2.97
    ।
    2.83
    ⚌
    2.69
     หรือ
    2.67
    ৭
    2.64
    𖣔
    2.59
    alties
    2.58
    Beskrivning
    2.55
    也非常
    2.53
    Activations Density 0.027%

    No Known Activations