© 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. 1194
    Prev
    Next
    INDEX
    Explanations

    you are stronger

    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
    <h2>
    0.88
     consider
    0.85
     mar
    0.78
     remote
    0.77
     art
    0.76
     인
    0.75
     bur
    0.75
    <h1>
    0.74
     bias
    0.73
     au
    0.72
    POSITIVE LOGITS
    Access
    1.18
    Students
    1.13
    Rod
    1.09
    Excellent
    1.06
    Secure
    1.06
    Student
    1.05
    students
    1.02
    Get
    1.00
    Registered
    1.00
    Prepare
    0.99
    Activations Density 0.000%

    No Known Activations