© 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-262K
    7. 111536
    Prev
    Next
    INDEX
    Explanations

    Weber, intense, Style, mass, cream, Whiskey

    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
     pant
    0.39
     compass
    0.39
    obu
    0.37
    變
    0.37
    ઞ
    0.37
    iones
    0.36
    hunt
    0.36
    During
    0.35
    €
    0.35
    ⁄
    0.35
    POSITIVE LOGITS
    ządu
    0.49
     Zust
    0.47
     Zustand
    0.46
     సౌ
    0.46
     Aussage
    0.46
     hätte
    0.45
    Ain
    0.45
     infraestructura
    0.45
     Allocated
    0.45
     দৃষ্টান্ত
    0.44
    Activations Density 0.002%

    No Known Activations