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. 17-GEMMASCOPE-2-RES-65K
    4. 47185
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions and states

    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_17_width_65k_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
    ل
    1.38
     vasos
    1.24
    ب
    1.24
    uing
    1.23
    Saldo
    1.23
    د
    1.21
    نا
    1.20
    Attention
    1.20
    ল
    1.18
    n
    1.18
    POSITIVE LOGITS
    și
    1.31
    o
    1.13
    şil
    1.13
    şi
    1.10
    ه
    1.07
     वहां
    1.05
     नियुक्त
    1.05
    ति
    1.05
    े
    1.02
     Streit
    1.01
    Activations Density 0.000%

    No Known Activations