© 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. 34-GEMMASCOPE-RES-131K
    7. 99423
    Prev
    Next
    INDEX
    Explanations

    official USA

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

    The neuron fires on the individual word‐pieces that make up multiword proper names or brands (e.g. “Naughty by Nature,” “Tik ka Take,” “BW API_bot,” “Strat for”), i.e. tokens belonging to named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    >%
    -0.95
    ()/
    -0.94
    assword
    -0.94
    ”),
    -0.93
    ”،
    -0.91
     فعل
    -0.89
    ])/
    -0.88
    霭
    -0.88
    kuuta
    -0.88
    %',
    -0.85
    POSITIVE LOGITS
    oficial
    1.09
     online
    0.97
    official
    0.96
     USA
    0.96
     officially
    0.95
    Official
    0.94
    Offic
    0.94
     официаль
    0.92
     Official
    0.91
    Global
    0.90
    Activations Density 0.042%

    No Known Activations