© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84562
    Prev
    Next
    INDEX
    Explanations

    people water

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

    The neuron strongly activates on first-person, self-referential language—especially “I” and related pronouns/constructions indicating the speaker talking about themselves.

    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
     kuliah
    -0.87
     load
    -0.86
    iseen
    -0.85
    료
    -0.84
     food
    -0.83
    Techniques
    -0.83
    wife
    -0.82
     vektör
    -0.81
     rock
    -0.81
     خونه
    -0.81
    POSITIVE LOGITS
    Whilst
    0.99
     slay
    0.97
     ATR
    0.96
     Britney
    0.95
    キム
    0.93
    twimg
    0.93
     gays
    0.90
     heifers
    0.89
     её
    0.89
     Gaga
    0.89
    Activations Density 0.029%

    No Known Activations