© 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. 76488
    Prev
    Next
    INDEX
    Explanations

    If you

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

    The neuron fires on second-person pronouns—particularly occurrences of “you.”

    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
    ESPEC
    -1.12
     Inoltre
    -0.99
    brada
    -0.96
    禰
    -0.89
     山田
    -0.88
    ODO
    -0.88
    Might
    -0.86
    :……
    -0.86
    Здра
    -0.85
    .」
    -0.84
    POSITIVE LOGITS
     ever
    1.85
     ask
    1.44
     want
    1.34
     haven
    1.33
     asked
    1.32
     read
    1.30
     told
    1.28
    有任何
    1.10
     asks
    1.10
     choć
    1.09
    Activations Density 0.034%

    No Known Activations