© 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. 963
    Prev
    Next
    INDEX
    Explanations

    Hem / hemi prefixes

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

    This neuron responds to occurrences of the substring “hem” (as in hemicellulose, Hempstead, or names starting with Hem).

    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
     水果
    -0.77
    名の
    -0.73
     आवश्यकता
    -0.71
    ṓ
    -0.71
     Συ
    -0.71
    ógicos
    -0.71
     درمانی
    -0.69
    Density
    -0.69
     Abbé
    -0.69
    δας
    -0.68
    POSITIVE LOGITS
     Hem
    0.96
    phite
    0.77
    demi
    0.76
     sharks
    0.76
     HEM
    0.75
     licencias
    0.75
    Hem
    0.74
     Haw
    0.72
     Compute
    0.71
    atite
    0.71
    Activations Density 0.030%

    No Known Activations