© 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. 86073
    Prev
    Next
    INDEX
    Explanations

    New Jersey

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

    The neuron fires on mentions of the place name “New Jersey” (including its abbreviation NJ).

    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
    नलोड
    -2.92
    ндарт
    -2.86
     Menschheit
    -2.69
    ᠂
    -2.58
    
    -2.53
    ⭓
    -2.45
    ꜄
    -2.34
    ୮
    -2.28
    埽
    -2.28
    
    -2.27
    POSITIVE LOGITS
    ra
    2.81
    These
    2.66
    What
    2.39
     Songtext
    2.30
    However
    2.28
    This
    2.19
    ↵
    2.14
    It
    2.13
    They
    2.05
     Commentaires
    2.05
    Activations Density 0.004%

    No Known Activations