© 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. 542
    Prev
    Next
    INDEX
    Explanations

    real estate, brands, and locations

    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
    久しぶりに
    -1.36
    今週
    -1.30
    今日も
    -1.27
    昨日の
    -1.27
    Зно
    -1.27
    昨日は
    -1.23
    aien
    -1.17
    asaran
    -1.16
    さぁ
    -1.15
    عالی
    -1.14
    POSITIVE LOGITS
    fourths
    1.16
    wisata
    1.12
    umers
    1.06
     hayan
    1.05
     évé
    1.04
    谷川
    1.04
     CREEK
    1.03
     .........
    1.03
    のように
    1.02
    Ǻ
    1.02
    Activations Density 0.015%

    No Known Activations