© 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. 9317
    Prev
    Next
    INDEX
    Explanations

    60 followed by units

    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
    羕
    -2.28
    .
    -2.22
     Entfer
    -2.20
    欲しい
    -2.19
     Bedürf
    -2.17
     Entscheid
    -2.17
     Diseño
    -2.13
    𐀀
    -2.13
     Können
    -2.11
    鹋
    -2.11
    POSITIVE LOGITS
    檮
    2.05
    ⽼
    1.96
     (…)
    1.95
     Songtext
    1.91
    an
    1.91
     :
    1.88
     anz
    1.84
     andra
    1.84
     uruguay
    1.80
     でも
    1.80
    Activations Density 0.023%

    No Known Activations