© 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. 10-GEMMASCOPE-RES-131K
    7. 73168
    Prev
    Next
    INDEX
    Explanations

    harboring

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

    The neuron fires specifically on occurrences of the verb “harboring” (and its British spelling “harbouring”), i.e. the present‐participle form of “harbor.”

    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
     sentra
    -2.30
     aussit
    -2.11
     kedai
    -2.08
     pneu
    -2.06
     kredit
    -2.02
     venezia
    -1.99
     stiker
    -1.98
    💚
    -1.95
     Departement
    -1.93
     INDONESIA
    -1.91
    POSITIVE LOGITS
     “
    2.00
     werden
    1.95
    ’
    1.85
    大声
    1.83
     ist
    1.80
     Diese
    1.77
     ,
    1.69
     en
    1.69
    就
    1.66
    たくさん
    1.65
    Activations Density 0.017%

    No Known Activations