© 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-65K
    7. 5138
    Prev
    Next
    INDEX
    Explanations

    time codes

    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
     Thak
    0.81
     hautes
    0.78
     specular
    0.77
    
    0.77
    <unused52>
    0.77
    izoph
    0.75
     winger
    0.75
    rxjs
    0.74
     compromise
    0.74
    ুক্তি
    0.74
    POSITIVE LOGITS
    ↵
    0.73
    previous
    0.72
    ↵↵
    0.71
    Previous
    0.70
    Triple
    0.70
    How
    0.67
    Efficiency
    0.67
    Mem
    0.66
    Hire
    0.66
    Identify
    0.65
    Activations Density 0.001%

    No Known Activations