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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13667
    Prev
    Next
    INDEX
    Explanations

    recipe links

    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
    ↵↵
    1.21
     Eleven
    0.84
     Merry
    0.84
     Alec
    0.82
     hydrogens
    0.82
    穎
    0.79
     Democrats
    0.79
     Four
    0.76
     LGBTQ
    0.76
     Hers
    0.75
    POSITIVE LOGITS
    <h2>
    1.47
    <h3>
    1.33
    *
    1.21
    <h6>
    1.12
    <h4>
    1.09
    Diagram
    1.04
    Feedback
    1.03
    <h5>
    1.02
    Attention
    0.99
    해야
    0.96
    Activations Density 0.000%

    No Known Activations