© 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. 86111
    Prev
    Next
    INDEX
    Explanations

    overseeing something

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

    The neuron fires on occurrences of the verb “oversee” (and its inflected forms like oversees, overseeing, oversaw), i.e. supervision-related terms.

    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
     If
    -3.09
    </b>
    -2.94
     When
    -2.63
     noteworthy
    -2.59
     That
    -2.48
    )
    -2.47
    }
    -2.31
     sizeable
    -2.28
    ”
    -2.27
     prominent
    -2.25
    POSITIVE LOGITS
    Ꮉ
    3.08
    
    2.97
    霂
    2.69
    錞
    2.64
    
    2.56
    蹓
    2.56
    METHODOLOGY
    2.55
     sprüche
    2.52
    ();
    2.52
    ครื่อง
    2.47
    Activations Density 0.002%

    No Known Activations