© 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. 22-GEMMASCOPE-RES-131K
    4. 73721
    Prev
    Next
    INDEX
    Explanations

    aspects of

    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
     or
    -2.27
     and
    -1.41
     или
    -1.23
     cucharadas
    -1.17
    weitere
    -1.14
    したり
    -1.13
    Komentar
    -1.10
     یا
    -1.09
     any
    -1.08
     atau
    -1.07
    POSITIVE LOGITS
     including
    2.33
    including
    2.06
    INCLUDING
    1.93
     INCLUDING
    1.88
    包括
    1.86
     incluyendo
    1.80
    Including
    1.79
     Including
    1.74
     včetně
    1.66
     включая
    1.63
    Activations Density 0.027%

    No Known Activations