© 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. 34-GEMMASCOPE-RES-131K
    7. 49298
    Prev
    Next
    INDEX
    Explanations

    students and pupils

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

    The neuron fires on tokens that occur in biographical life‐events statements (e.g. “was,” “is,” “been,” “student,” “teacher,” “born,” “died”).

    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
    พ่อ
    -0.78
     отец
    -0.78
    controllers
    -0.77
    册
    -0.77
    Contributor
    -0.77
    vriende
    -0.75
    Experts
    -0.74
    LocationManager
    -0.74
    isexual
    -0.71
     แม่
    -0.71
    POSITIVE LOGITS
     students
    4.41
     pupils
    3.61
     student
    3.44
     pupil
    3.28
    students
    3.08
     Students
    2.86
     alumnos
    2.83
    Students
    2.80
    生徒
    2.78
     disciples
    2.69
    Activations Density 0.046%

    No Known Activations