© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99215
    Prev
    Next
    INDEX
    Explanations

    Combine

    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
     '
    -2.64
    也
    -2.33
     naszych
    -2.06
    一个
    -1.94
    on
    -1.91
     
    -1.91
    actéristi
    -1.88
     ‘
    -1.86
     \
    -1.84
    ^{
    -1.82
    POSITIVE LOGITS
    ⦊
    2.09
    却被
    2.08
    ྂ
    1.99
    mechanism
    1.91
    𝟭
    1.88
    dzić
    1.86
    mappedBy
    1.85
     fossa
    1.84
    屜
    1.80
    ORPG
    1.79
    Activations Density 0.015%

    No Known Activations