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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3789
    Prev
    Next
    INDEX
    Explanations

    supply chain issues

    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_22_width_16k_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
    gpg
    1.20
    ubern
    1.10
     platoon
    1.09
    eneuve
    1.08
    𝗶
    1.07
    hamburger
    1.05
    minded
    1.03
    lunch
    1.02
     জুল
    1.00
    Derek
    0.98
    POSITIVE LOGITS
    wght
    1.20
     çeşitli
    1.01
    쳐
    0.97
     Wszyst
    0.93
     난
    0.92
    ेंजर
    0.91
     Blink
    0.91
     Οι
    0.90
    መሪያ
    0.88
    𝙴
    0.87
    Activations Density 0.000%

    No Known Activations