Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36966
    Prev
    Next
    INDEX
    Explanations

    bureaucratic inertia and creativity

    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
    }=$
    0.50
    asyarakat
    0.46
    缺乏
    0.45
     सक्रिय
    0.44
    Ladder
    0.44
    Treat
    0.43
    juang
    0.43
     провер
    0.43
    Synt
    0.43
     अवश्य
    0.42
    POSITIVE LOGITS
     SKU
    0.48
     year
    0.48
     tangy
    0.45
     halv
    0.45
     シ
    0.44
     CRT
    0.44
    ଙ
    0.43
     rendering
    0.43
     ọ
    0.43
     servi
    0.43
    Activations Density 0.002%

    No Known Activations