© 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. 14767
    Prev
    Next
    INDEX
    Explanations

    officially announcing or deciding

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

    The neuron detects formal “news‐style” action verbs expressing official or reported activities (e.g. proposed, dropped, announced, released, filed, found).

    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
     its
    -1.68
    它的
    -1.28
     your
    -1.23
     their
    -1.20
     itself
    -1.13
     ప
    -1.12
    自分
    -1.09
    its
    -1.09
     ourselves
    -1.03
    Its
    -1.02
    POSITIVE LOGITS
     himself
    2.55
    himself
    1.93
     his
    1.66
     himſelf
    1.41
    herself
    1.19
     herself
    1.14
     chaussures
    1.11
     ему
    1.09
     egli
    1.08
    彼の
    1.05
    Activations Density 0.076%

    No Known Activations