© 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. 110904
    Prev
    Next
    INDEX
    Explanations

    mx graph parameter files

    np_acts-logits-general · gemini-2.5-flash-lite

    the text "mx" in code and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </i>
    -2.58
    -2.48
     a
    -2.47
    ࿆
    -2.47
    さんから
    -2.36
    垕
    -2.34
    犼
    -2.33
    鹮
    -2.31
     estándares
    -2.30
    schrank
    -2.27
    POSITIVE LOGITS
    翃
    2.47
    ?"
    2.33
    踌
    2.14
    yskland
    2.11
     fueron
    2.09
    嵓
    2.08
    窺
    2.06
     și
    2.06
    的高度
    2.03
    ".
    2.00
    Activations Density 0.003%

    No Known Activations