© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 53942
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and 'all'

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

    This neuron responds to transcript or document metadata markers—especially numeric labels, timestamps (digits and colons), section numbers, and other header‐style tokens.

    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
     kompeti
    -1.12
     psychologie
    -1.09
    inin
    -1.08
    璈
    -1.06
     ouver
    -1.06
    iacute
    -1.04
    klassi
    -1.04
    耷
    -1.04
    loggen
    -1.04
    拵
    -1.03
    POSITIVE LOGITS
     there
    1.39
    copg
    1.29
     this
    1.12
     types
    1.10
     who
    1.09
    锁定
    1.08
     presented
    1.08
     which
    1.02
     again
    1.02
     discussed
    1.00
    Activations Density 0.005%

    No Known Activations