© 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. 56027
    Prev
    Next
    INDEX
    Explanations

    Postmenopausal, fat cell, human monoclonal

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

    copyright notices and legal text in source code files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily responds to numeric tokens (especially individual digits and year 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_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
    ändern
    -0.82
    isBlank
    -0.82
    owano
    -0.81
    campista
    -0.77
    noční
    -0.77
     Poland
    -0.76
     fé
    -0.75
    ļa
    -0.73
    iteln
    -0.73
    maier
    -0.73
    POSITIVE LOGITS
    GOOGLE
    1.16
     STL
    1.14
    STL
    1.07
     GOOGLE
    1.05
    Missouri
    1.02
    ofür
    0.95
    reflection
    0.90
     プリント
    0.90
    ">/
    0.89
     сдела
    0.87
    Activations Density 0.016%

    No Known Activations