© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72689
    Prev
    Next
    INDEX
    Explanations

    names starting with Kh

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

    The neuron activates on proper names or words beginning with the letters “Kh,” such as “Khan,” “Khuda,” or “Khurasan.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -3.20
    ”
    -2.81
    Here
    -2.75
    one
    -2.73
    ),
    -2.72
    In
    -2.72
    !
    -2.72
     With
    -2.69
    $
    -2.67
     was
    -2.66
    POSITIVE LOGITS
    
    3.08
    ᠂
    2.94
    硨
    2.84
     抠
    2.81
    犼
    2.80
    鱨
    2.63
     夜景
    2.52
    ᛬
    2.48
     帅气
    2.45
     広場
    2.42
    Activations Density 0.010%

    No Known Activations