© 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. 119848
    Prev
    Next
    INDEX
    Explanations

    capabilities, info, id, properties

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

    technical terms and identifiers related to system capabilities, configuration, and information (like "capability", "capabilities", "cpuid", "info", "CONFIG", "version", "architecture", and "proc/cpuinfo").

    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
     We
    -1.91
    </i>
    -1.88
    JspWriter
    -1.56
     to
    -1.55
     who
    -1.42
     was
    -1.40
    たちが
    -1.40
    我都
    -1.40
    "));
    -1.39
     خواهد
    -1.34
    POSITIVE LOGITS
     diki
    1.84
     tabak
    1.71
     nena
    1.59
     ceket
    1.56
     akrab
    1.52
     transparan
    1.49
     morts
    1.48
     politika
    1.47
     abiye
    1.45
     there
    1.41
    Activations Density 0.031%

    No Known Activations