© 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. 102325
    Prev
    Next
    INDEX
    Explanations

    projects and Prometheus

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

    the word "project" or its translations in Romance languages (proyecto, projet, projeto).

    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
    2
    -3.52
    a
    -3.20
    r
    -3.03
    with
    -3.00
    S
    -2.97
    3
    -2.97
    0
    -2.92
    C
    -2.89
    N
    -2.84
    4
    -2.84
    POSITIVE LOGITS
    ჻
    3.27
    鲥
    3.09
     spezielle
    3.03
     offizielle
    2.97
     unangemessene
    2.95
    ᆞ
    2.94
     mauva
    2.86
     vollständige
    2.83
    贻
    2.81
     größere
    2.80
    Activations Density 0.002%

    No Known Activations