© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70236
    Prev
    Next
    INDEX
    Explanations

    the only way

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

    The neuron detects phrases expressing exclusivity or inevitability, such as “only one thing to do,” “could only mean one thing,” or “only way.”

    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
     面包
    -1.41
    )–
    -1.39
    呶
    -1.38
    often
    -1.34
    merkung
    -1.34
    羕
    -1.32
    .–
    -1.32
    ardez
    -1.31
    感じで
    -1.29
     ?
    -1.28
    POSITIVE LOGITS
     when
    2.17
     this
    1.92
     that
    1.66
     from
    1.65
     people
    1.54
    <
    1.47
     by
    1.35
     through
    1.35
     for
    1.34
    "
    1.34
    Activations Density 0.032%

    No Known Activations