© 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. 10-GEMMASCOPE-RES-131K
    7. 13334
    Prev
    Next
    INDEX
    Explanations

    know how

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

    The neuron strongly responds to occurrences of the phrase “know how” (including its split or hyphenated forms).

    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
     the
    -2.11
    '
    -1.91
     multifaceted
    -1.85
    ]
    -1.82
    刋
    -1.80
    when
    -1.78
     notable
    -1.77
     stating
    -1.76
     noteworthy
    -1.73
    }
    -1.73
    POSITIVE LOGITS
     tarefas
    2.27
     Là
    1.98
    .’”
    1.88
    KNOW
    1.87
     situações
    1.86
    ⚌
    1.84
    
    1.82
    𐄁
    1.79
    ⟣
    1.79
    ↵↵
    1.76
    Activations Density 0.003%

    No Known Activations