© 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. 68363
    Prev
    Next
    INDEX
    Explanations

    left accident scene

    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
    曏
    -1.25
     already
    -1.24
     sánh
    -1.17
    鄖
    -1.15
    マヨ
    -1.15
    ひた
    -1.14
     portugal
    -1.14
    吅
    -1.13
     megjelen
    -1.13
    唢
    -1.12
    POSITIVE LOGITS
     to
    2.17
    left
    1.30
     on
    1.29
     meses
    1.28
     left
    1.26
     “
    1.23
    蒨
    1.22
     their
    1.20
     Left
    1.20
     geografic
    1.16
    Activations Density 0.045%

    No Known Activations