© 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. 22-GEMMASCOPE-RES-131K
    7. 39145
    Prev
    Next
    INDEX
    Explanations

    "not sure" or confirmations

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

    The neuron identifies speaker-attribution labels in dialogue (i.e. a character’s name followed by a colon).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    使いやすい
    -1.06
    キャンセル
    -0.97
     feltro
    -0.97
     therefore
    -0.97
    Поэтому
    -0.96
    Вита
    -0.96
    fortunate
    -0.95
     kado
    -0.94
     nevertheless
    -0.94
     Therefore
    -0.94
    POSITIVE LOGITS
     will
    1.58
     would
    1.48
     daarvoor
    1.23
     if
    1.15
     
    1.05
     ancak
    1.02
     allerede
    1.00
     impossible
    1.00
     do
    0.99
     no
    0.98
    Activations Density 0.020%

    No Known Activations