© 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. 95365
    Prev
    Next
    INDEX
    Explanations

    Ohhhh, nope, love

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

    The neuron is keyed to personal pronouns and direct-address words (e.g. I, you, we, my) signaling first‐ and second‐person references.

    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
     goddamn
    -1.36
     ludicrous
    -1.34
    ぱ
    -1.30
     cérami
    -1.29
     sekunder
    -1.28
     savag
    -1.27
     voyant
    -1.26
    ℣
    -1.26
     originalen
    -1.24
     crucial
    -1.23
    POSITIVE LOGITS
     it
    1.49
    !!
    1.45
     just
    1.38
    !!!
    1.30
    \},
    1.27
     or
    1.25
     most
    1.24
     during
    1.23
    !
    1.22
     More
    1.20
    Activations Density 0.140%

    No Known Activations