© 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. 10560
    Prev
    Next
    INDEX
    Explanations

    bring useful things

    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
     there
    -1.48
     эти
    -1.45
     it
    -1.44
     diese
    -1.30
     это
    -1.30
    粉色
    -1.30
    ositol
    -1.28
    ="
    -1.27
    -1.23
    RIQUE
    -1.22
    POSITIVE LOGITS
    bring
    2.00
     Brings
    1.98
     Bring
    1.91
     Brought
    1.85
     BRING
    1.72
    Bring
    1.62
     to
    1.59
     bring
    1.59
     brought
    1.32
     along
    1.31
    Activations Density 0.055%

    No Known Activations