© 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. 10-GEMMASCOPE-RES-131K
    7. 21835
    Prev
    Next
    INDEX
    Explanations

    filenames and code snippets

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

    The neuron fires strongly on capitalized lexical tokens (proper names or technical terms).

    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
    翾
    -3.08
    ༔
    -3.03
    酲
    -2.98
    🦣
    -2.98
    辚
    -2.98
    雠
    -2.97
    鳊
    -2.94
    鸲
    -2.91
    沨
    -2.88
    裢
    -2.84
    POSITIVE LOGITS
    1
    4.50
    t
    3.81
    9
    3.63
    7
    3.55
    2
    3.48
    5
    3.48
    s
    3.41
    8
    3.31
    ll
    3.27
    3
    3.23
    Activations Density 0.012%

    No Known Activations