© 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. 34-GEMMASCOPE-RES-131K
    7. 26000
    Prev
    Next
    INDEX
    Explanations

    book spines

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

    The neuron detects and highlights numeric or metadata tokens—especially dates, version numbers, and other parenthesized numerical information.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     پہ
    -0.78
    椭
    -0.78
    订阅
    -0.75
    MSP
    -0.73
    PUBLISHED
    -0.73
     Publications
    -0.72
     publications
    -0.71
    ング
    -0.71
     TAB
    -0.70
     féminin
    -0.70
    POSITIVE LOGITS
     spine
    0.90
    Spine
    0.89
     spines
    0.89
    spine
    0.85
     Spine
    0.83
    ಝ
    0.83
     Harlequin
    0.82
     jm
    0.81
    горе
    0.79
    udh
    0.78
    Activations Density 0.048%

    No Known Activations