© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38991
    Prev
    Next
    INDEX
    Explanations

    distribution and circulation

    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
    ↵↵
    -2.02
     he
    -1.40
    oceros
    -1.34
     his
    -1.34
     WHO
    -1.26
     date
    -1.24
     instruções
    -1.23
    jestel
    -1.22
    ли
    -1.20
     enchanted
    -1.20
    POSITIVE LOGITS
    different
    1.52
    ẾT
    1.48
    大家好
    1.38
     помогает
    1.38
     zoveel
    1.36
    ayaquil
    1.35
     "---
    1.32
    Răsp
    1.31
     LABEL
    1.29
     レモン
    1.29
    Activations Density 0.044%

    No Known Activations