© 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. 130081
    Prev
    Next
    INDEX
    Explanations

    rank, score, or first

    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
    beitet
    -1.06
     today
    -1.00
    achte
    -0.94
     muchacha
    -0.93
     аса
    -0.90
    ͌
    -0.88
    zą
    -0.88
     already
    -0.88
    了一
    -0.86
     now
    -0.85
    POSITIVE LOGITS
     vždy
    1.66
     zawsze
    1.66
     either
    1.64
     либо
    1.52
    either
    1.46
     each
    1.44
     sempre
    1.41
     souvent
    1.40
     всегда
    1.38
     spesso
    1.38
    Activations Density 0.036%

    No Known Activations