© 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. 131
    Prev
    Next
    INDEX
    Explanations

    Dopamine, Multidrug, Q:

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

    uppercase letters in cryptographic keys and encoded data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     could
    -2.86
     gets
    -2.81
     has
    -2.78
     Both
    -2.64
     went
    -2.64
     Although
    -2.63
     exuberant
    -2.63
     should
    -2.59
     may
    -2.58
     horrific
    -2.58
    POSITIVE LOGITS
    ܆
    3.14
    厹
    3.13
    憷
    2.91
    ︐
    2.80
     amd
    2.75
    簓
    2.72
    possibly
    2.70
    鲩
    2.70
     dando
    2.63
    ’
    2.63
    Activations Density 0.033%

    No Known Activations