© 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. 86097
    Prev
    Next
    INDEX
    Explanations

    Spielberg, Hiroshima, LPS

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

    The neuron fires strongly on named entities—proper names (like “Spielberg”), places (“Hiroshima”), disease or chemical terms (“cholera,” “LPS”), and other specific entity tokens.

    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
     This
    -3.13
     When
    -2.53
    t
    -2.45
    ’
    -2.27
    This
    -2.20
     '
    -2.09
    ſelves
    -2.06
     nourished
    -2.03
     construed
    -2.02
     THE
    -1.98
    POSITIVE LOGITS
    1
    2.44
     technischen
    2.42
    蒹
    2.33
    ྕ
    2.27
     nowej
    2.22
     nowych
    2.22
     vollständ
    2.22
    袛
    2.20
    いろんな
    2.16
     تعدى
    2.14
    Activations Density 0.004%

    No Known Activations