© 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. 163
    Prev
    Next
    INDEX
    Explanations

    common words followed by verbs

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

    The neuron is strongly activated by first- and second-person pronouns (e.g. “I,” “you,” “me”) in song lyrics.

    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
     avulla
    -1.27
     EACH
    -1.15
    很是
    -1.13
     poign
    -1.13
     apparaissent
    -1.12
     deviennent
    -1.11
    ぶつ
    -1.11
     devenir
    -1.11
     plastiques
    -1.11
     utilisent
    -1.06
    POSITIVE LOGITS
     on
    1.81
     in
    1.51
     all
    1.46
     always
    1.38
     probably
    1.30
     for
    1.28
     after
    1.28
     usually
    1.25
     where
    1.23
     almost
    1.23
    Activations Density 0.015%

    No Known Activations