© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    The neuron selectively activates on longer, content‐bearing nouns and noun phrases—especially formal, technical, or topic‐specific 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
    さんを
    -1.41
     are
    -1.34
    mockMvc
    -1.33
     we
    -1.32
    di
    -1.27
    mi
    -1.23
     gena
    -1.22
     nozze
    -1.22
    con
    -1.20
    available
    -1.20
    POSITIVE LOGITS
     and
    1.73
     colorear
    1.59
     burbujas
    1.45
     insumos
    1.41
     videojuegos
    1.38
     cilindros
    1.38
     zelo
    1.38
     former
    1.36
     residuos
    1.34
     imprimible
    1.33
    Activations Density 0.077%

    No Known Activations