© 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. 12834
    Prev
    Next
    INDEX
    Explanations

    posting forum content

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

    The neuron fires on the forum “posting” count badges (e.g. “Posting 234”, “posting 222”, etc.), i.e. tokens showing a user’s post‐count number.

    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
    The
    -2.81
    ים
    -2.72
    arraycopy
    -2.55
    Ｕ
    -2.53
    最大
    -2.52
    他
    -2.48
    あり
    -2.28
    笄
    -2.27
    綽
    -2.27
    mathcal
    -2.25
    POSITIVE LOGITS
    慊
    2.80
    ↵
    2.69
    勦
    2.66
    珖
    2.56
    絝
    2.56
    搥
    2.55
    </h3>
    2.53
     generando
    2.45
    灕
    2.45
    眼下
    2.44
    Activations Density 0.015%

    No Known Activations