© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9991
    Prev
    Next
    INDEX
    Explanations

    research funding agencies and programs

    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
     penghar
    -1.53
    itize
    -1.48
    these
    -1.45
    ﺅ
    -1.37
    izes
    -1.32
    ous
    -1.30
    dos
    -1.29
     trå
    -1.28
     globale
    -1.28
    ldots
    -1.28
    POSITIVE LOGITS
     tamamen
    1.33
    起了
    1.26
    bague
    1.24
     Gebet
    1.21
    冰冰
    1.20
    losed
    1.20
    巍
    1.19
     including
    1.18
    chelsea
    1.16
     “
    1.14
    Activations Density 0.057%

    No Known Activations