© 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. 76928
    Prev
    Next
    INDEX
    Explanations

    official titles and events

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

    This neuron fires on key content words in a news report—especially place names, official agencies, and other salient 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
     дуже
    -1.37
    歿
    -1.34
     superbly
    -1.31
     monies
    -1.28
     our
    -1.23
     asap
    -1.23
     skall
    -1.21
     läßt
    -1.20
     навіть
    -1.20
     Xmas
    -1.19
    POSITIVE LOGITS
     —
    1.83
     Wednesday
    1.55
     “(
    1.48
     COVID
    1.48
    “(
    1.47
     “[
    1.43
     "(
    1.42
     said
    1.41
     ​​
    1.41
     Tuesday
    1.36
    Activations Density 0.101%

    No Known Activations