© 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. 60562
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by enough

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

    This neuron activates on single-word descriptive adjectives (e.g. fast, old, strong, large, brave, bulky).

    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
     suicidio
    -1.84
    himself
    -1.66
     firſt
    -1.64
     fevere
    -1.55
     firft
    -1.47
     Mère
    -1.46
     libur
    -1.45
     velkommen
    -1.44
     onsdag
    -1.44
     maquilla
    -1.44
    POSITIVE LOGITS
     enough
    2.89
     komór
    1.66
     podem
    1.64
    name
    1.54
     qualquer
    1.52
    -,
    1.47
    runken
    1.46
     -,
    1.46
    -\\
    1.45
    来て
    1.45
    Activations Density 0.034%

    No Known Activations