© 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. 85530
    Prev
    Next
    INDEX
    Explanations

    informal items or technical 'stuff'

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

    The neuron fires on the informal filler noun “stuff.”

    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
    ان
    -3.17
    0
    -2.59
    皤
    -2.55
    蠵
    -2.39
    趼
    -2.34
    G
    -2.30
    A
    -2.19
     diskusi
    -2.19
    蕺
    -2.19
    ２
    -2.16
    POSITIVE LOGITS
    </h3>
    2.39
     amending
    2.13
    といふ
    2.13
    StoryboardSegue
    2.13
     ignite
    2.03
    /';
    2.03
    ュー
    2.02
    埽
    1.95
    })
    1.93
     känns
    1.93
    Activations Density 0.004%

    No Known Activations