© 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. 13536
    Prev
    Next
    INDEX
    Explanations

    advice appreciated

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

    The neuron fires on occurrences of the word “advice” (including variants like “Advice” or “advices”).

    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
    我也是
    -2.52
     wodurch
    -2.48
     –
    -2.44
     —
    -2.42
    我又
    -2.36
    (
    -2.33
     womit
    -2.31
    ’
    -2.31
     «
    -2.30
    ′
    -2.30
    POSITIVE LOGITS
    .
    4.28
    you
    2.94
    ጵ
    2.70
     soñar
    2.56
    いかない
    2.56
    Ꞓ
    2.53
    你
    2.50
    貍
    2.47
     miesięcy
    2.38
     内衣
    2.33
    Activations Density 0.005%

    No Known Activations