© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50213
    Prev
    Next
    INDEX
    Explanations

    saving practices ambitions goals

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ম্ব
    0.54
     红
    0.47
    ir
    0.46
     उल्टा
    0.45
    画
    0.43
    alan
    0.43
    ار
    0.43
     Ideally
    0.43
     Sorrow
    0.42
    aru
    0.42
    POSITIVE LOGITS
     предостав
    0.50
     depred
    0.48
     обу
    0.47
    lebnis
    0.45
     disposto
    0.43
     Pasand
    0.43
     рит
    0.42
    šení
    0.42
    蓮
    0.41
    🧒
    0.41
    Activations Density 0.001%

    No Known Activations