© 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. 37977
    Prev
    Next
    INDEX
    Explanations

    collective bargaining

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

    task, humiliation, acquisitions, insult

    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
    ויות
    0.50
    痿
    0.46
    攙
    0.44
    Descripción
    0.43
    त्तर
    0.43
    虧
    0.42
    ない
    0.42
    וי
    0.42
     vacío
    0.42
     друзей
    0.42
    POSITIVE LOGITS
     daher
    0.50
    বেলা
    0.50
     atthe
    0.48
     scorsa
    0.47
     اللاعب
    0.47
     recoveries
    0.46
     Zustand
    0.46
     STORAGE
    0.46
     offizi
    0.46
     wholesalers
    0.46
    Activations Density 0.000%

    No Known Activations