© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    json objects and arrays

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

    numeric values in JSON data structures, particularly zeros and single-digit numbers appearing as property values.

    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
    </strong>
    -1.99
     all
    -1.80
    at
    -1.77
    虽然
    -1.72
    be
    -1.72
     will
    -1.66
    。”
    -1.64
    or
    -1.54
    </b>
    -1.54
    менту
    -1.53
    POSITIVE LOGITS
    瘰
    2.08
    蟥
    2.02
     schnelle
    2.00
     hochwertige
    1.88
     barcos
    1.86
     verbess
    1.80
     dnes
    1.75
     constantemente
    1.74
     salvajes
    1.74
     Vordergrund
    1.73
    Activations Density 0.026%

    No Known Activations