© 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. 41771
    Prev
    Next
    INDEX
    Explanations

    UnityEngine and pygame code

    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
    u
    -2.63
    '
    -2.45
    訁
    -2.36
    section
    -2.31
     was
    -2.17
    l
    -2.17
    饪
    -2.14
     :/
    -2.11
    甚至
    -2.09
     standout
    -2.03
    POSITIVE LOGITS
    .
    3.75
    ︲
    2.66
    蜑
    2.38
    殽
    2.34
    褙
    2.30
    镚
    2.28
    啣
    2.27
     eenvou
    2.23
    蘼
    2.22
     ſta
    2.20
    Activations Density 0.001%

    No Known Activations