© 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. 43276
    Prev
    Next
    INDEX
    Explanations

    names starting with Ham

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

    The neuron strongly activates on any token containing the subword “Ham” (e.g. Ham, Hammond, Hamza, Hamcrest).

    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
    ⸫
    -3.61
     unſ
    -3.41
     ſever
    -3.27
     แต่
    -3.17
    䊐
    -3.02
     periódicos
    -3.00
     テープ
    -2.94
    臯
    -2.91
     alojamientos
    -2.86
    ⩕
    -2.86
    POSITIVE LOGITS
    ),
    3.55
    the
    3.50
     When
    3.39
    x
    3.34
    t
    3.00
    \
    2.89
    1
    2.83
     Despite
    2.78
    >
    2.75
     During
    2.70
    Activations Density 0.012%

    No Known Activations