© 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. 113110
    Prev
    Next
    INDEX
    Explanations

    Mark, Matthew, ACT

    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
    {
    -1.65
    *
    -1.42
     ว่า
    -1.38
    そこは
    -1.34
    similar
    -1.31
    --"
    -1.31
    大事な
    -1.30
    柔らかい
    -1.29
    —“
    -1.28
    勿論
    -1.25
    POSITIVE LOGITS
    琹
    1.80
    కర్య
    1.79
    ጾ
    1.72
    mockMvc
    1.63
    Suomen
    1.61
    聍
    1.61
     nesten
    1.53
    sukienka
    1.52
    ᨗ
    1.50
    寕
    1.48
    Activations Density 0.011%

    No Known Activations