© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107446
    Prev
    Next
    INDEX
    Explanations

    adjusting or adjusted

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

    The neuron activates on occurrences of the root “adjust,” including its inflected and derived forms (e.g. adjust, adjusted, adjustment).

    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
     вони
    -1.10
    erintah
    -1.09
     odes
    -1.07
     síntesis
    -1.06
     placid
    -1.06
     porción
    -1.02
     embellished
    -1.01
     Absicht
    -1.01
     copii
    -1.00
    Plates
    -1.00
    POSITIVE LOGITS
     Adjust
    1.67
    adjust
    1.64
     adjust
    1.54
    Adjust
    1.50
     adjusts
    1.41
    谞
    1.36
     Adjustment
    1.32
     to
    1.26
    ments
    1.25
    调整
    1.25
    Activations Density 0.009%

    No Known Activations