© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    development contexts

    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_9_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
    ání
    1.75
    醚
    1.71
    Decrement
    1.67
    unción
    1.54
    োস
    1.51
    
    1.46
     abe
    1.44
     cognit
    1.44
    lini
    1.42
     ইনি
    1.42
    POSITIVE LOGITS
     предложить
    1.76
    𝐑
    1.72
    ्हा
    1.68
    时候
    1.67
    нес
    1.67
    酛
    1.64
    あまり
    1.60
    스
    1.52
     بڑا
    1.50
     தவிர
    1.47
    Activations Density 0.021%

    No Known Activations