© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50213
    Prev
    Next
    INDEX
    Explanations

    emotional states and abstract concepts

    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_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
    ম্ব
    0.52
    ار
    0.45
    ir
    0.44
     उल्टा
    0.43
     typewriter
    0.43
    画
    0.43
    alan
    0.42
     camera
    0.42
     Ideally
    0.41
     fortitude
    0.41
    POSITIVE LOGITS
     предостав
    0.46
     depred
    0.46
    šení
    0.44
    lebnis
    0.44
    Depois
    0.44
    兘
    0.43
    Questo
    0.42
     disposto
    0.42
     Pasand
    0.41
    หล่ง
    0.41
    Activations Density 0.000%

    No Known Activations