© 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. 22-GEMMASCOPE-RES-131K
    4. 36431
    Prev
    Next
    INDEX
    Explanations

    brand names, software, and universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ところに
    -2.22
    の方も
    -1.83
    向けの
    -1.77
    感じで
    -1.76
    んですよね
    -1.70
    感じが
    -1.69
    ところは
    -1.68
    の方に
    -1.64
    んでしょう
    -1.61
    に入れ
    -1.56
    POSITIVE LOGITS
    🤘
    1.45
    😝
    1.37
    などなど
    1.37
    omato
    1.36
    などが
    1.36
    があり
    1.35
    😜
    1.35
    umers
    1.33
    thodoxy
    1.27
    茄子
    1.27
    Activations Density 0.104%

    No Known Activations