© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9138
    Prev
    Next
    INDEX
    Explanations

    projection or project

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

    The neuron fires whenever it sees numeric literals or tokens containing numbers.

    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
    拮
    -2.78
    激烈
    -2.75
    内外
    -2.64
    同上
    -2.63
    反抗
    -2.53
    翆
    -2.44
    恫
    -2.42
    痦
    -2.42
    桎
    -2.41
    抉
    -2.38
    POSITIVE LOGITS
    
    3.00
    "
    2.89
    甞
    2.69
    —
    2.66
    ㋛
    2.61
    癭
    2.52
    u
    2.50
    小孩子
    2.47
     kostenlosen
    2.41
    很难
    2.39
    Activations Density 0.001%

    No Known Activations