© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3023
    Prev
    Next
    INDEX
    Explanations

    important notes

    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
    step
    0.74
     either
    0.67
    first
    0.66
     step
    0.64
    ②
    0.63
    either
    0.63
    1
    0.62
    ?
    0.61
    ①
    0.60
    ✓
    0.60
    POSITIVE LOGITS
     Additional
    1.74
     Important
    1.67
     Further
    1.61
     Conclusions
    1.49
     Conclusion
    1.46
    Additional
    1.45
     additional
    1.41
     इंपोर्टेंट
    1.40
     Things
    1.39
     Links
    1.39
    Activations Density 0.324%

    No Known Activations