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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1005
    Prev
    Next
    INDEX
    Explanations

    Eiffel Tower context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     college
    0.71
    Acetoxy
    0.71
     antim
    0.71
     কলেজ
    0.70
     Gobern
    0.68
    쩜
    0.68
    })$;
    0.67
    })}$
    0.66
    可能是
    0.65
    יא
    0.64
    POSITIVE LOGITS
     during
    1.20
     During
    1.06
     inside
    1.05
     within
    1.04
     Having
    1.01
     durante
    1.01
     throughout
    1.00
    Having
    0.99
     because
    0.99
     from
    0.97
    Activations Density 0.000%

    No Known Activations