© 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. 22-GEMMASCOPE-RES-131K
    7. 26739
    Prev
    Next
    INDEX
    Explanations

    exercises and problems

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

    The neuron is keyed to textbook exercise references (terms like “exercise” or “ex.” and their accompanying problem numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’
    -1.13
    vernote
    -1.02
    vajú
    -0.87
     Armee
    -0.86
     meetings
    -0.85
     felpa
    -0.85
    handleClose
    -0.85
     efforts
    -0.83
     everything
    -0.82
     Gebä
    -0.82
    POSITIVE LOGITS
     задачи
    1.28
     posed
    1.26
    oncé
    1.23
     questions
    1.19
    opheles
    1.16
     worded
    1.10
    练习
    1.09
     Question
    1.07
     задания
    1.07
    ícil
    1.06
    Activations Density 0.048%

    No Known Activations