© 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. 10-GEMMASCOPE-RES-131K
    4. 42658
    Prev
    Next
    INDEX
    Explanations

    affirming statement

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

    The neuron fires on emphatic agreement or affirmation phrases (e.g. “that’s right,” “perfectly true,” 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_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
     "
    -1.59
     เขา
    -1.39
    sys
    -1.33
    ه
    -1.31
    м
    -1.30
     -
    -1.30
     donde
    -1.28
    ]
    -1.28
    ̼
    -1.23
    就知道
    -1.22
    POSITIVE LOGITS
    你能
    1.37
     complemento
    1.35
    」、「
    1.34
     contactar
    1.34
     Entrée
    1.31
     but
    1.28
    But
    1.27
    💯
    1.27
     ""))
    1.25
     Informações
    1.22
    Activations Density 0.020%

    No Known Activations