© 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. 111063
    Prev
    Next
    INDEX
    Explanations

    menstrual cycle strength

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

    content related to fitness, bodybuilding, and muscle training.

    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
     السياس
    -1.95
    וּ
    -1.59
     パソコン
    -1.56
     while
    -1.52
     حکومت
    -1.46
    ﻹ
    -1.45
    examples
    -1.42
    uchten
    -1.31
    ᾽
    -1.31
     Theologie
    -1.30
    POSITIVE LOGITS
    🩱
    1.84
    ׄ
    1.55
    🩴
    1.49
    ција
    1.47
    為に
    1.46
     چربی
    1.44
     reafon
    1.41
    ]={
    1.39
     مباراة
    1.38
     سينما
    1.37
    Activations Density 0.137%

    No Known Activations