© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6167
    Prev
    Next
    INDEX
    Explanations

    list items and structure

    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_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
    nivers
    0.82
     ataupun
    0.80
     :-)
    0.80
     igual
    0.79
    🤛
    0.78
     headquartered
    0.78
     which
    0.77
     :).
    0.76
     عزیز
    0.76
     customarily
    0.75
    POSITIVE LOGITS
    <i>
    1.28
    <em>
    1.22
     /*
    1.04
    <strong>
    1.04
     *
    0.98
    Avg
    0.97
    <b>
    0.96
     -->
    0.93
     
    0.92
     •
    0.91
    Activations Density 0.734%

    No Known Activations