© 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. 34-GEMMASCOPE-RES-131K
    7. 117502
    Prev
    Next
    INDEX
    Explanations

    transforming or redefining

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

    The neuron fires on words signaling major change or transformation—terms like transform, redefine, revolutionize, modernize, change, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     изпъл
    -0.94
    hichever
    -0.93
     Eintrag
    -0.84
    遯
    -0.84
     either
    -0.82
    这时候
    -0.80
     řed
    -0.80
    ctie
    -0.80
    либо
    -0.79
    の場合は
    -0.79
    POSITIVE LOGITS
     how
    1.95
     traditional
    1.59
    traditional
    1.38
    Traditional
    1.38
     тради
    1.34
    how
    1.25
     approaches
    1.23
     sposób
    1.19
    conventional
    1.18
     نحوه
    1.16
    Activations Density 0.117%

    No Known Activations