© 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. 99189
    Prev
    Next
    INDEX
    Explanations

    names beginning with Ha

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

    This neuron detects capitalized name fragments beginning with “Ha” (as in surnames like Ha, Hawkes, Harrigan, Hawkins, etc.).

    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
     pemimpin
    -0.83
    ்கு
    -0.81
    H
    -0.81
     H
    -0.80
     sabid
    -0.78
    crimson
    -0.75
     ha
    -0.75
    HYDR
    -0.74
     devastation
    -0.74
     hanya
    -0.73
    POSITIVE LOGITS
    اشق
    0.74
    Ther
    0.73
     getStart
    0.71
    võ
    0.71
    轮回
    0.71
     vuotta
    0.70
     יח
    0.70
     landen
    0.69
     APPELLANT
    0.69
    aire
    0.69
    Activations Density 0.041%

    No Known Activations