© 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. 111196
    Prev
    Next
    INDEX
    Explanations

    introducing citations or examples

    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
    籐
    -2.48
    撚
    -2.20
    衿
    -2.13
    *}[
    -2.05
     áreas
    -1.97
    และ
    -1.92
     reduce
    -1.91
     и
    -1.91
     ingredientes
    -1.91
     minimize
    -1.90
    POSITIVE LOGITS
    ’
    3.22
    依照
    2.38
    퐼
    2.36
    說
    2.36
    絎
    2.31
    っている
    2.30
     EIGHT
    2.20
    廡
    2.20
    已经是
    2.20
    an
    2.20
    Activations Density 0.014%

    No Known Activations