© 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. 105884
    Prev
    Next
    INDEX
    Explanations

    personal names: Angus, Lucy, Jenny

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

    The neuron selectively fires on specific capitalized proper names (notably “Angus” and “Lucy”).

    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
    We
    -3.67
    Because
    -3.31
    0
    -3.30
    To
    -3.27
    But
    -3.20
    1
    -3.19
    When
    -3.17
    With
    -3.14
    After
    -3.11
    For
    -3.09
    POSITIVE LOGITS
    玙
    2.83
    ).
    2.72
    咐
    2.63
     самая
    2.55
    ++];
    2.55
     котором
    2.52
    oriques
    2.47
    竺
    2.45
     was
    2.45
     is
    2.45
    Activations Density 0.007%

    No Known Activations