© 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. 12509
    Prev
    Next
    INDEX
    Explanations

    technical lists or components

    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
    夢見
    -1.16
    کفش
    -1.13
    ویژگی
    -1.13
    ~ 
    -1.09
    というわけで
    -1.09
    Fakta
    -1.06
    ⇰
    -1.05
    giày
    -1.03
     when
    -1.01
    خخ
    -1.01
    POSITIVE LOGITS
    including
    1.08
    ファー
    0.99
    «
    0.98
     incluyendo
    0.98
     крупных
    0.95
     «
    0.94
    ทั้ง
    0.94
     toutes
    0.94
     компания
    0.94
    both
    0.93
    Activations Density 0.015%

    No Known Activations