© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57611
    Prev
    Next
    INDEX
    Explanations

    internal feelings and states

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

    The neuron strongly responds to longer, content-heavy tokens—especially multisyllabic words and extended punctuation like double dashes—i.e. it picks out long, substantive bits of text.

    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
    ري
    -0.95
     traite
    -0.94
    revel
    -0.90
    اول
    -0.88
     Comfor
    -0.87
     voors
    -0.86
     partant
    -0.85
     Reconciliation
    -0.83
     italy
    -0.81
     everything
    -0.80
    POSITIVE LOGITS
    )))))
    0.93
    菓
    0.91
     mga
    0.89
     geen
    0.88
    /}
    0.84
     malignant
    0.78
     reflections
    0.78
     accord
    0.78
     Дер
    0.78
     лишь
    0.77
    Activations Density 0.124%

    No Known Activations