© 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. 259
    Prev
    Next
    INDEX
    Explanations

    followed by

    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
     its
    -1.48
    畵
    -1.43
     jego
    -1.38
    してみて
    -1.38
    ducer
    -1.37
    shmi
    -1.36
    ulasi
    -1.31
    puestas
    -1.30
     hence
    -1.29
     menghasilkan
    -1.28
    POSITIVE LOGITS
    \
    1.45
    -
    1.41
    ,
    1.39
    lovely
    1.25
     personer
    1.24
    ꪔ
    1.21
    đ
    1.21
    si
    1.19
     seksual
    1.16
    ージャー
    1.16
    Activations Density 0.029%

    No Known Activations