© 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. 9748
    Prev
    Next
    INDEX
    Explanations

    describing correctness and normality

    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
     also
    -1.89
     também
    -1.47
     I
    -1.32
     about
    -1.28
     également
    -1.27
    ва
    -1.25
     along
    -1.24
    ulite
    -1.23
     també
    -1.21
     religión
    -1.20
    POSITIVE LOGITS
    although
    1.56
    ★★★★☆
    1.36
    Despite
    1.34
     boda
    1.27
    𐐪
    1.24
    There
    1.24
     despite
    1.22
    Väl
    1.22
    ที่ยว
    1.21
    жешь
    1.21
    Activations Density 0.198%

    No Known Activations