© 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. 99767
    Prev
    Next
    INDEX
    Explanations

    as ... the

    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
     including
    -1.46
    Some
    -1.46
    谞
    -1.35
    Waktu
    -1.27
    Jangan
    -1.27
    Beberapa
    -1.27
    Several
    -1.26
     using
    -1.25
    不管是
    -1.25
    Kegiatan
    -1.24
    POSITIVE LOGITS
     “
    1.75
     "
    1.43
     his
    1.37
     ”
    1.36
     systèmes
    1.31
     '
    1.30
     «
    1.29
    }=\
    1.23
     mesmo
    1.23
    "]="
    1.19
    Activations Density 0.046%

    No Known Activations