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. 29-GEMMASCOPE-2-RES-65K
    4. 1821
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms

    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_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
     Chevy
    1.06
     ameryka
    0.97
     تطوير
    0.94
     Hadoop
    0.91
     brainstorm
    0.91
     reimag
    0.91
     serendip
    0.91
    <unused632>
    0.89
    糟糕
    0.89
     biznes
    0.89
    POSITIVE LOGITS
     unjustified
    0.95
     judicial
    0.93
     probative
    0.90
     obligatory
    0.88
     obliged
    0.85
     duly
    0.83
     obligation
    0.83
     procedural
    0.81
     registered
    0.80
     pursuant
    0.80
    Activations Density 0.119%

    No Known Activations