© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5494
    Prev
    Next
    INDEX
    Explanations

    list of best/prominent

    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_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
    insurer
    0.94
    ivores
    0.93
    <unused1296>
    0.93
    oxide
    0.91
    <unused1691>
    0.90
    <unused1612>
    0.90
    <unused1391>
    0.88
    <unused1717>
    0.88
    
    0.88
    <unused852>
    0.87
    POSITIVE LOGITS
     COVID
    0.89
     Scottish
    0.88
     Japanese
    0.87
     modern
    0.86
     Christian
    0.85
     българ
    0.84
     the
    0.84
     basketball
    0.83
    0.81
     Canadian
    0.80
    Activations Density 4.740%

    No Known Activations