© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 195188
    Prev
    Next
    INDEX
    Explanations

    foreign/specific linguistic elements

    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
     executives
    0.42
     officers
    0.40
     shoes
    0.40
     roles
    0.38
     criminal
    0.38
    ={},
    0.38
     weddings
    0.38
     politicians
    0.37
     kriminal
    0.37
     inform
    0.37
    POSITIVE LOGITS
    WAR
    0.45
    IDAY
    0.42
     Aquarius
    0.40
    Հ
    0.40
     συμ
    0.38
     തിരഞ്ഞെടു
    0.38
    യിരുന്നു
    0.38
    UTRON
    0.38
    鄧
    0.38
    Expl
    0.37
    Activations Density 0.000%

    No Known Activations