© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131961
    Prev
    Next
    INDEX
    Explanations

    reports and dashboards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وە
    0.42
     स्वरों
    0.41
     ঘন্
    0.41
    ᅯ
    0.41
     হুগলীর
    0.40
     VESSELS
    0.40
    OWER
    0.40
    瑆
    0.39
    ))%>%
    0.39
    웰
    0.39
    POSITIVE LOGITS
     Colorado
    0.41
     содержание
    0.39
    ед
    0.39
    Colorado
    0.38
    етра
    0.38
     at
    0.38
     upon
    0.38
    ოდ
    0.38
     comprensión
    0.38
     Siena
    0.37
    Activations Density 0.000%

    No Known Activations