© 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. 22-GEMMASCOPE-RES-131K
    7. 128160
    Prev
    Next
    INDEX
    Explanations

    time off and leave

    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
     الماء
    -1.26
    zwi
    -1.09
    ographia
    -1.03
     seleccionar
    -1.02
     barbati
    -1.01
    ступила
    -0.98
    〖
    -0.98
     próprias
    -0.97
    味的
    -0.96
    ㄉ
    -0.96
    POSITIVE LOGITS
     leave
    1.29
    ススメ
    1.20
    seeable
    1.16
    employees
    1.15
     period
    1.14
     for
    1.12
     calendar
    1.10
    公司
    1.09
    idious
    1.09
    ranslated
    1.09
    Activations Density 0.015%

    No Known Activations