© 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. 53-GEMMASCOPE-2-RES-262K
    7. 66474
    Prev
    Next
    INDEX
    Explanations

    indices i and j

    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_53_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
    䧺
    0.39
    銖
    0.38
     Vag
    0.37
    शेद
    0.36
     Gnome
    0.36
     lewis
    0.36
    ၼ်
    0.36
    APPE
    0.36
    鯢
    0.36
     Garth
    0.36
    POSITIVE LOGITS
    IJ
    2.55
     IJ
    2.55
    ij
    2.53
     ij
    2.42
     Ij
    2.30
    Ij
    2.28
     Bij
    1.96
    ija
    1.91
    Bij
    1.87
     Vij
    1.85
    Activations Density 0.014%

    No Known Activations