© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72500
    Prev
    Next
    INDEX
    Explanations

    for a

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

    This neuron fires on mentions of organizations or locations (proper-name entities like company names, city names, divisions, etc.).

    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
    ैसे
    -1.31
    4
    -1.28
    ("
    -1.27
    7
    -1.27
    5
    -1.27
     on
    -1.24
    2
    -1.23
     THESE
    -1.23
    3
    -1.18
     evidente
    -1.17
    POSITIVE LOGITS
     élas
    1.39
    because
    1.35
     who
    1.33
     caseros
    1.31
     voldoende
    1.29
    vaného
    1.28
    teinte
    1.27
     físicos
    1.25
     it
    1.24
    Because
    1.24
    Activations Density 0.090%

    No Known Activations