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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49128
    Prev
    Next
    INDEX
    Explanations

    technical packing and code context

    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_31_width_65k_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
     heartbreak
    0.47
    Amanda
    0.46
    월
    0.45
     heartbroken
    0.45
    बा
    0.43
    ría
    0.43
     Katherine
    0.43
     обита
    0.43
    </strong>
    0.42
    October
    0.42
    POSITIVE LOGITS
     bushings
    0.53
     dienen
    0.48
     workpiece
    0.48
     används
    0.47
     sensores
    0.47
     изделия
    0.46
     actuators
    0.46
     assemblies
    0.46
     يمكن
    0.46
     gauges
    0.46
    Activations Density 0.015%

    No Known Activations