© 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. 34-GEMMASCOPE-RES-131K
    7. 78136
    Prev
    Next
    INDEX
    Explanations

    reasonable or rational judgment

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

    The neuron fires on normative or legalistic evaluative phrases—e.g. idioms like “reasonable persons would …” or “in his right mind” that express what a typical or reasonable person thinks.

    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
     några
    -0.94
    illoin
    -0.90
    benen
    -0.89
    şa
    -0.88
     tableta
    -0.88
    suits
    -0.84
    biggest
    -0.84
    heiten
    -0.83
    ribution
    -0.83
     TECHN
    -0.81
    POSITIVE LOGITS
     reasonable
    3.22
     sane
    3.13
     sensible
    2.83
     rational
    2.75
    reasonable
    2.47
     intelligent
    2.38
     Reasonable
    2.25
    Reasonable
    2.05
    rational
    2.00
     decent
    1.90
    Activations Density 0.052%

    No Known Activations