© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111735
    Prev
    Next
    INDEX
    Explanations

    birthweight placental weight

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

    CSS properties related to typography and font styling.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on isolated code identifiers—individual programming‐language keywords or property names (e.g., style, tie, variant).

    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
    of
    -2.41
    </i>
    -2.39
     cuando
    -2.08
     This
    -2.08
    el
    -1.95
     aufgrund
    -1.90
    ti
    -1.88
     unprecedented
    -1.82
    time
    -1.81
    om
    -1.80
    POSITIVE LOGITS
    橚
    1.95
    锇
    1.90
    
    1.89
    鈇
    1.89
    鱨
    1.88
    ൎ
    1.81
     كبيرة
    1.80
     animés
    1.80
     armados
    1.78
    ‪.‬‬
    1.77
    Activations Density 0.001%

    No Known Activations