© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12451
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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_10/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
    -
    -1.95
    0
    -1.88
    ,“
    -1.84
    )
    -1.84
    1
    -1.81
    ra
    -1.77
     zobac
    -1.77
    er
    -1.74
    la
    -1.73
    -1.71
    POSITIVE LOGITS
     firmado
    1.85
     identificado
    1.76
     determinadas
    1.70
     urgencia
    1.70
    事が
    1.65
     certitude
    1.64
    ﹁
    1.64
     observado
    1.64
     respaldo
    1.63
    齶
    1.63
    Activations Density 0.005%

    No Known Activations