© 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. 103343
    Prev
    Next
    INDEX
    Explanations

    body's condition or state

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

    references to the human body and its physical state or functioning.

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

    The neuron primarily activates on occurrences of the word “body.”

    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
    jmniej
    -1.59
     wła
    -1.54
    šení
    -1.52
     hingga
    -1.52
    𞤢
    -1.48
    ㈡
    -1.41
    据
    -1.41
    
    -1.38
    ਆ
    -1.38
     adanya
    -1.38
    POSITIVE LOGITS
    踱
    1.72
    }
    1.57
    Parameteri
    1.56
     meilleur
    1.56
     Einzelnen
    1.55
    ⸨
    1.55
     negativa
    1.54
     участников
    1.54
     будущего
    1.53
    婀
    1.52
    Activations Density 0.010%

    No Known Activations