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. 1015
    Prev
    Next
    INDEX
    Explanations

    listing countries and data

    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
    靣
    0.86
     despatched
    0.86
     cowl
    0.82
    Invoice
    0.79
    Metallic
    0.78
    Laptop
    0.76
    }`)
    0.74
    Residence
    0.73
    掮
    0.73
    붐
    0.72
    POSITIVE LOGITS
     narrow
    0.72
     casi
    0.71
     everything
    0.69
     bad
    0.69
     Sometimes
    0.65
     They
    0.63
     Another
    0.63
     still
    0.62
     Unless
    0.62
     depression
    0.62
    Activations Density 0.000%

    No Known Activations