© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129211
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially detecting the demonstrative “This,” especially when it appears at the start of a sentence.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     obiec
    -1.40
     necessarie
    -1.27
    ̳
    -1.20
     zove
    -1.16
     désormais
    -1.14
     papir
    -1.12
    헷
    -1.09
    ële
    -1.09
     νό
    -1.07
     bahkan
    -1.06
    POSITIVE LOGITS
     is
    2.41
     was
    1.72
     happened
    1.49
     didn
    1.43
     wasn
    1.34
     shouldn
    1.34
     isn
    1.33
     meant
    1.23
     couldn
    1.20
    Ketika
    1.19
    Activations Density 0.067%

    No Known Activations