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. 910
    Prev
    Next
    INDEX
    Explanations

    would you like

    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
    虽然
    0.84
     относя
    0.80
    雖然
    0.80
    <unused681>
    0.76
     Baru
    0.76
     nemo
    0.75
     虽然
    0.75
     cheeky
    0.73
    :‏
    0.72
    ‏:‏
    0.71
    POSITIVE LOGITS
     appreciates
    0.99
     evaluate
    0.98
     appreciate
    0.98
     utilized
    0.93
     utilize
    0.93
     permitted
    0.90
     desire
    0.88
     possess
    0.87
     require
    0.87
     requested
    0.85
    Activations Density 0.009%

    No Known Activations