© 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. 34-GEMMASCOPE-RES-131K
    7. 103018
    Prev
    Next
    INDEX
    Explanations

    Of course, I can

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

    The neuron is mainly triggered by personal pronouns—especially first-person references like “I” and “we.”

    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
     actually
    -1.73
     dokonce
    -1.70
     apparently
    -1.63
     jopa
    -1.63
     навіть
    -1.59
     Parece
    -1.55
     действительно
    -1.54
     Apparently
    -1.53
     perhaps
    -1.51
    確かに
    -1.50
    POSITIVE LOGITS
     also
    1.25
     puisque
    1.20
     then
    1.18
     никакого
    1.16
     puisqu
    1.13
     også
    1.13
     essendo
    1.09
    也
    1.09
    Needless
    1.09
     nothing
    1.09
    Activations Density 0.036%

    No Known Activations