© 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. 22-GEMMASCOPE-RES-131K
    7. 12527
    Prev
    Next
    INDEX
    Explanations

    UTF-8 encoding

    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
    После
    -1.25
     otro
    -1.19
     vá
    -1.13
     rocas
    -1.11
     hatten
    -1.07
     muros
    -1.05
     representado
    -1.05
    !”
    -1.05
     holand
    -1.05
     tantos
    -1.04
    POSITIVE LOGITS
    鲠
    1.27
    aphne
    1.23
    Skocz
    1.22
    店長
    1.18
    &__
    1.18
     accents
    1.18
    mius
    1.17
    érrez
    1.16
    ifies
    1.13
    娌
    1.13
    Activations Density 0.002%

    No Known Activations