© 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. 22-GEMMASCOPE-RES-131K
    7. 14163
    Prev
    Next
    INDEX
    Explanations

    cars involved in accidents or parked

    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_22/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
    WATER
    -1.13
    鐽
    -1.11
    cinoma
    -1.06
     startDate
    -1.02
    тие
    -1.02
    ztés
    -1.02
    gebracht
    -1.02
     estreno
    -1.02
     allemaal
    -1.02
     sabo
    -1.01
    POSITIVE LOGITS
     containing
    1.35
     belonging
    1.34
     parked
    1.26
     other
    1.20
     Jurí
    1.16
     owner
    1.12
     owned
    1.09
     three
    1.06
     σας
    1.05
    常见的
    1.05
    Activations Density 0.034%

    No Known Activations