© 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. 22-GEMMASCOPE-RES-131K
    4. 36255
    Prev
    Next
    INDEX
    Explanations

    secondary treatments after

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

    The neuron fires on tokens that denote repetition or recurrence—words like “relapse,” “repeat,” “revision,” or references to a second or repeated procedure.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vorüber
    -1.02
     supply
    -0.91
    繡
    -0.91
    結果は
    -0.90
     daarom
    -0.88
    锁定
    -0.86
     wyłą
    -0.85
    рення
    -0.85
    <bos>
    -0.85
     einzigen
    -0.85
    POSITIVE LOGITS
     after
    1.59
     повтор
    1.28
    После
    1.27
    Después
    1.26
     después
    1.23
    二次
    1.21
     second
    1.20
     после
    1.19
     вже
    1.18
    Secondary
    1.17
    Activations Density 0.100%

    No Known Activations