© 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. 10246
    Prev
    Next
    INDEX
    Explanations

    Pil and related words

    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
    𖤍
    -2.17
    '
    -2.16
     \
    -2.14
    猡
    -2.13
     hennes
    -2.11
    .
    -2.11
     annuel
    -2.09
    ௜
    -2.06
     santuario
    -2.06
     \
    -2.02
    POSITIVE LOGITS
    illots
    2.39
    li
    2.28
    j
    2.27
     이미
    2.22
     dwells
    2.22
     ligeramente
    2.20
    ING
    2.20
     curvy
    2.16
     Если
    2.13
     acrobat
    2.11
    Activations Density 0.005%

    No Known Activations