© 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. 104421
    Prev
    Next
    INDEX
    Explanations

    describing appearance or style

    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
    Although
    -2.44
    ௅
    -2.16
    Despite
    -2.09
    ization
    -2.08
     Although
    -1.98
    lgari
    -1.98
     häufigsten
    -1.94
    壜
    -1.92
    waite
    -1.91
    Contrary
    -1.88
    POSITIVE LOGITS
     или
    2.61
     atau
    2.55
     oder
    2.44
    หรือ
    2.34
    或者
    2.28
     veya
    2.14
     یا
    2.08
    “
    2.08
    或
    2.06
    一旁
    2.05
    Activations Density 0.022%

    No Known Activations