© 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. 74720
    Prev
    Next
    INDEX
    Explanations

    places and file system operations

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

    The neuron activates on distinct named entities—especially proper nouns like geographic place names or brand/project names.

    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
    .《
    -3.03
    ⬈
    -3.00
    ጺ
    -2.91
    棪
    -2.88
    鸶
    -2.83
    ⻬
    -2.83
     粥
    -2.80
    ୩
    -2.80
    pulseira
    -2.77
    戋
    -2.75
    POSITIVE LOGITS
    1
    3.44
    6
    3.22
    3
    3.11
    9
    3.09
    you
    3.05
    8
    3.00
     The
    2.97
     [
    2.88
    7
    2.84
     '
    2.80
    Activations Density 0.040%

    No Known Activations