© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103074
    Prev
    Next
    INDEX
    Explanations

    quoted words and phrases

    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
    
    -2.33
    ⟣
    -2.28
     häufigsten
    -2.19
    xvii
    -2.11
     การ
    -2.06
     Quando
    -2.02
    乄
    -1.98
    
    -1.98
     The
    -1.96
     indepen
    -1.95
    POSITIVE LOGITS
     substantial
    2.13
    just
    2.09
    〜〜
    2.05
    and
    1.99
    that
    1.99
     cheerful
    1.91
    While
    1.91
    ness
    1.88
     high
    1.84
     получает
    1.84
    Activations Density 0.048%

    No Known Activations