© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11922
    Prev
    Next
    INDEX
    Explanations

    positive evaluations and outcomes

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

    The neuron is keyed to positive evaluative or praise words conveying approval or admiration.

    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
    Specifik
    -0.97
    Enders
    -0.97
     WITHOUT
    -0.96
     ángeles
    -0.94
     kvadrat
    -0.93
     perangkat
    -0.93
    lación
    -0.93
     fön
    -0.92
    nó
    -0.92
    öra
    -0.91
    POSITIVE LOGITS
     work
    1.81
     to
    1.80
     job
    1.77
     that
    1.48
     seeing
    1.45
     choice
    1.43
    !
    1.23
     contribution
    1.16
     hearing
    1.15
     effort
    1.11
    Activations Density 0.017%

    No Known Activations