© 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. 10-GEMMASCOPE-RES-131K
    7. 7921
    Prev
    Next
    INDEX
    Explanations

    state of being

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

    The neuron is highly sensitive to the noun “state,” especially in phrases like “state of ….”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     empê
    -2.08
    糁
    -2.03
    隂
    -1.96
    蛲
    -1.95
    耵
    -1.95
    konferenz
    -1.95
     exécut
    -1.93
     causando
    -1.92
    sprzedam
    -1.92
     脸
    -1.91
    POSITIVE LOGITS
     you
    2.28
     impeccable
    1.95
     españolas
    1.91
    та
    1.84
    ”
    1.84
     extranjeros
    1.80
    山上
    1.80
     leur
    1.80
     на
    1.77
    “
    1.77
    Activations Density 0.049%

    No Known Activations