© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104600
    Prev
    Next
    INDEX
    Explanations

    have to

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

    The neuron fires on the phrase “have to” (i.e. constructions expressing obligation/necessity).

    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
    L
    -1.83
    d
    -1.79
    N
    -1.75
    in
    -1.70
    F
    -1.62
    D
    -1.57
    ↵
    -1.56
    W
    -1.53
    E
    -1.52
    S
    -1.47
    POSITIVE LOGITS
    觚
    1.82
    vestres
    1.80
    empt
    1.77
    卺
    1.73
     nôtre
    1.73
     vôtre
    1.73
    upuncture
    1.72
     différent
    1.71
     jednej
    1.68
    下载附件
    1.67
    Activations Density 0.028%

    No Known Activations