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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12270
    Prev
    Next
    INDEX
    Explanations

    demographics and age groups

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     its
    -0.96
     userDao
    -0.92
     Ausbau
    -0.91
     Eigentü
    -0.85
     about
    -0.84
     such
    -0.84
     similar
    -0.82
     what
    -0.81
     for
    -0.80
    range
    -0.79
    POSITIVE LOGITS
     tromper
    0.96
     minggu
    0.90
    ඕ
    0.88
     perspek
    0.87
     ones
    0.87
     motocicletas
    0.87
    COLOUR
    0.86
     couvercle
    0.85
     jullie
    0.84
     bebek
    0.84
    Activations Density 0.084%

    No Known Activations