© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129982
    Prev
    Next
    INDEX
    Explanations

    entitled to know or have

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

    The neuron is keyed to words and word-pairs expressing legal or formal entitlement (especially the phrase “entitled to”).

    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
    It
    -2.22
    9
    -1.77
    alisco
    -1.77
    ptonshire
    -1.70
     khỏ
    -1.68
     mę
    -1.66
    amable
    -1.64
     From
    -1.63
     sterben
    -1.62
     TO
    -1.61
    POSITIVE LOGITS
    
    2.14
    辚
    2.11
    skate
    1.97
     betek
    1.88
     eſſ
    1.85
    tasting
    1.82
     dezelve
    1.82
    谖
    1.81
    ejercicio
    1.79
    lised
    1.78
    Activations Density 0.006%

    No Known Activations