© 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. 34-GEMMASCOPE-RES-131K
    7. 64503
    Prev
    Next
    INDEX
    Explanations

    f, fo, fog, fod, fou, floy

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

    The neuron detects occurrences of the letter sequence “fog” (in any casing or as part of longer words).

    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
    參考資料
    -0.77
     Being
    -0.73
     schmerz
    -0.72
     positive
    -0.71
    就业
    -0.71
     lucky
    -0.70
     muster
    -0.70
    Being
    -0.70
    менения
    -0.68
     PyLong
    -0.68
    POSITIVE LOGITS
    gangss
    0.77
    सम
    0.75
    tistic
    0.75
    peace
    0.74
     Fog
    0.73
     הארץ
    0.72
    ਗ
    0.72
    aterdag
    0.71
    ospital
    0.71
    يميديا
    0.70
    Activations Density 0.023%

    No Known Activations