© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41703
    Prev
    Next
    INDEX
    Explanations

    itself / themselves

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

    This neuron strongly activates on capitalized names and technical abbreviations (proper nouns, acronyms, and scientific 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
    Джере
    -1.42
    ラックス
    -1.36
    elaar
    -1.35
    ᚺ
    -1.35
    ⬮
    -1.30
    STRUCTOR
    -1.27
    Allez
    -1.27
    Begriff
    -1.27
     lavable
    -1.27
     jadx
    -1.27
    POSITIVE LOGITS
     on
    1.35
     one
    1.35
     available
    1.30
     in
    1.26
    :
    1.25
     itself
    1.23
     its
    1.20
     he
    1.18
     into
    1.14
     without
    1.13
    Activations Density 0.310%

    No Known Activations