© 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. 99831
    Prev
    Next
    INDEX
    Explanations

    inventing and invented things

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

    The neuron fires on occurrences of “invent” and its morphological variants (e.g. inventing, invented, inventive).

    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
    2
    -3.58
    </b>
    -3.42
    _
    -3.09
    3
    -3.06
    er
    -2.97
    =
    -2.83
    ه
    -2.70
    ll
    -2.66
    *
    -2.64
    S
    -2.56
    POSITIVE LOGITS
    ússia
    2.92
    采用了
    2.75
    🢒
    2.64
    🕗
    2.59
     recibido
    2.58
    氲
    2.56
    
    2.52
    乀
    2.48
    簣
    2.45
    </h3>
    2.38
    Activations Density 0.017%

    No Known Activations