© 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. 129764
    Prev
    Next
    INDEX
    Explanations

    product descriptors and technical terms

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

    The neuron fires on passive‐voice or impersonal constructions—i.e. auxiliary “be” and “might” plus past-participle verbs (e.g. “are created,” “encoded,” “be restricted”).

    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
     -
    -2.58
    婞
    -2.36
    ৢ
    -2.22
    ༷
    -2.22
    擻
    -2.20
    ᠊
    -2.19
     bessere
    -2.19
     Vielfalt
    -2.17
     intentar
    -2.17
     $^{
    -2.14
    POSITIVE LOGITS
    y
    3.59
    ia
    2.91
    
    2.77
    re
    2.67
    嘬
    2.66
    te
    2.59
    ’，
    2.56
    r
    2.47
    z
    2.41
    他自己
    2.30
    Activations Density 0.015%

    No Known Activations