© 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. 2845
    Prev
    Next
    INDEX
    Explanations

    muscle and custom cars

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

    The neuron spots extreme or superlative descriptors (words emphasizing the highest degree, like “ultimate,” “fiercest,” “most,” “fastest,” 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
     Cessna
    -0.98
     Djokovic
    -0.89
     Boeing
    -0.85
    opes
    -0.82
     costitu
    -0.79
     honda
    -0.79
     midi
    -0.78
    inosau
    -0.78
     Madonna
    -0.77
     Aldi
    -0.77
    POSITIVE LOGITS
     muscle
    1.45
    muscle
    1.09
     customised
    1.04
     Muscle
    1.01
     replica
    1.00
     customized
    0.98
    Muscle
    0.97
    Customized
    0.96
     hear
    0.94
     custom
    0.91
    Activations Density 0.034%

    No Known Activations