© 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. 77126
    Prev
    Next
    INDEX
    Explanations

    out of context or phase

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

    The neuron detects the phrase “out of” (as in “taken out of context,” “out of phase,” “out of all proportion,” etc.).

    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
     fevereiro
    -0.89
     novembro
    -0.88
     dezembro
    -0.87
     março
    -0.85
     julho
    -0.81
     junho
    -0.78
    stacles
    -0.75
     incluem
    -0.75
    сный
    -0.75
    جوايز
    -0.73
    POSITIVE LOGITS
     out
    6.47
     Out
    3.45
    Out
    3.41
    OutOf
    3.00
     outta
    2.94
    out
    2.89
     OUT
    2.70
     fuori
    2.52
     fuera
    2.33
    OUT
    2.09
    Activations Density 0.074%

    No Known Activations