© 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. 14570
    Prev
    Next
    INDEX
    Explanations

    assembling or creating something

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

    The neuron fires on instances of the phrase “put together” (including “putting together”).

    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
    7
    -2.75
    2
    -2.59
    e
    -2.55
    9
    -2.31
    ’
    -2.27
    ought
    -2.22
    .
    -2.20
     一
    -2.20
    to
    -2.19
    <b>
    -2.14
    POSITIVE LOGITS
     Like
    2.36
    ornadas
    2.33
     Also
    2.25
     painfully
    2.11
     However
    2.09
    níka
    2.06
    icksburg
    2.06
    ⃟
    2.03
    älfte
    2.03
    unteers
    2.03
    Activations Density 0.003%

    No Known Activations