© 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. 105217
    Prev
    Next
    INDEX
    Explanations

    Angus, Laguna, ECC

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

    The neuron fires on capitalized names or acronyms (proper nouns and technical identifiers).

    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
    และ
    -2.66
    腠
    -2.61
     mengapa
    -2.36
    锨
    -2.31
    鎳
    -2.28
    TryDecode
    -2.25
     puntata
    -2.22
    ل
    -2.20
    ſelves
    -2.17
    ми
    -2.16
    POSITIVE LOGITS
    d
    3.41
    _
    3.05
    F
    2.83
    K
    2.81
    2
    2.80
    U
    2.70
    c
    2.70
    O
    2.64
    1
    2.63
    '
    2.61
    Activations Density 0.027%

    No Known Activations