© 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. 104473
    Prev
    Next
    INDEX
    Explanations

    column definitions and types

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

    references to database or data structure columns in technical code and 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
     encompasses
    -1.76
     or
    -1.67
    {
    -1.65
     unequivocally
    -1.62
     kept
    -1.62
     includes
    -1.61
     persino
    -1.61
    特定的
    -1.60
     fühlte
    -1.59
    Three
    -1.55
    POSITIVE LOGITS
    </strong>
    1.84
    ⁶
    1.80
    -
    1.77
    ⢅
    1.65
    ⁴
    1.63
    </i>
    1.63
     ],
    1.63
    釭
    1.57
    鞨
    1.57
     THINGS
    1.57
    Activations Density 0.000%

    No Known Activations