© 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. 29867
    Prev
    Next
    INDEX
    Explanations

    linking concepts with actions

    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
    ى
    0.49
     ett
    0.42
    λ
    0.41
    業務
    0.38
    로서
    0.38
     roles
    0.37
    ，
    0.37
     profiles
    0.37
    充
    0.37
    长
    0.36
    POSITIVE LOGITS
     声
    0.59
     продолжает
    0.53
    岖
    0.52
     זי
    0.51
     刺繍
    0.51
    掳
    0.50
     ပြ
    0.49
     продолжа
    0.49
     coração
    0.49
     monstru
    0.49
    Activations Density 0.001%

    No Known Activations