© 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. 50947
    Prev
    Next
    INDEX
    Explanations

    example questions and answers

    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
    ToProps
    0.43
    辇
    0.41
    Repair
    0.39
    קס
    0.39
     굉장히
    0.39
    ન્ટ
    0.38
     تشتغل
    0.38
    ﻔ
    0.38
     Vineyard
    0.38
     گلو
    0.38
    POSITIVE LOGITS
     oldest
    0.42
     batas
    0.40
     abolished
    0.38
     subtypes
    0.38
     নিষিদ্ধ
    0.36
     গিয়াছেন
    0.36
     restrictions
    0.36
    Exception
    0.35
     consent
    0.35
    詡
    0.35
    Activations Density 0.001%

    No Known Activations