© 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. 29098
    Prev
    Next
    INDEX
    Explanations

    data integrity and type information

    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_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
    '
    -2.02
    );
    -1.95
    Before
    -1.84
    Waktu
    -1.83
    ,
    -1.77
    2
    -1.75
    With
    -1.73
    When
    -1.69
    They
    -1.68
    除了
    -1.68
    POSITIVE LOGITS
     Perſ
    1.84
     Reſ
    1.68
     sabias
    1.68
     Inſ
    1.67
    鲧
    1.66
    댔
    1.59
    aise
    1.55
     ziua
    1.45
     hijas
    1.45
     ”
    1.45
    Activations Density 0.000%

    No Known Activations