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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7106
    Prev
    Next
    INDEX
    Explanations

    then think it step by step

    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
    د
    1.84
     তাহলে
    1.80
    р
    1.79
    ר
    1.65
    𝘢
    1.52
     అయితే
    1.45
    場合に
    1.42
    那就
    1.40
    𝘴
    1.39
    లో
    1.38
    POSITIVE LOGITS
    selves
    2.41
     proceeded
    2.03
     lintas
    1.98
     disinfect
    1.90
    ardier
    1.77
     proceed
    1.70
     proced
    1.69
    း
    1.69
     promptly
    1.67
     /^
    1.64
    Activations Density 0.035%

    No Known Activations