© 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. 34-GEMMASCOPE-RES-131K
    7. 2584
    Prev
    Next
    INDEX
    Explanations

    programmes and performances

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

    The neuron fires on words conveying positive, upbeat sentiment (e.g. enjoy, pleasant, good cheer).

    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
     celebración
    -0.92
    振り返
    -0.85
     внутріш
    -0.85
    Preferred
    -0.83
     кілька
    -0.83
    lanz
    -0.79
     cambiare
    -0.78
    ológicos
    -0.78
     Preferred
    -0.77
     Unterlagen
    -0.77
    POSITIVE LOGITS
    Refresh
    1.05
     Refresh
    1.04
    Programme
    1.00
     programme
    0.99
     programma
    0.97
     entertainment
    0.91
     refreshments
    0.90
     Programme
    0.90
     programmes
    0.89
     contributed
    0.84
    Activations Density 0.007%

    No Known Activations