© 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. 22-GEMMASCOPE-RES-131K
    7. 14494
    Prev
    Next
    INDEX
    Explanations

    school, children, parents, students

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

    The neuron fires strongly on mentions of school‐related items and costs—e.g. supplies, fees, lunches, materials—i.e. references to school expenses and resources.

    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
    ⌬
    -1.54
     erzeugen
    -1.31
    否认
    -1.27
    而后
    -1.25
    亟
    -1.24
    还没
    -1.23
    怼
    -1.22
     juft
    -1.21
    捅
    -1.18
     yng
    -1.17
    POSITIVE LOGITS
     school
    2.27
     children
    1.79
     students
    1.70
     our
    1.59
     parents
    1.52
    PUESTA
    1.45
     Belakang
    1.45
    局长
    1.43
     these
    1.38
     student
    1.38
    Activations Density 0.009%

    No Known Activations