© 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. 12685
    Prev
    Next
    INDEX
    Explanations

    needed to ground

    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
    ↵↵↵
    -1.37
    ');
    -1.36
     collè
    -1.34
    そちら
    -1.31
     trhu
    -1.29
     cosas
    -1.23
     ARISING
    -1.23
    Jakie
    -1.22
     cheminée
    -1.22
    eload
    -1.19
    POSITIVE LOGITS
     at
    1.51
    .
    1.38
     in
    1.35
    もいい
    1.21
     one
    1.14
     ofrecen
    1.13
    if
    1.11
    xyl
    1.10
    wale
    1.09
    quirrel
    1.09
    Activations Density 0.051%

    No Known Activations