Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7332
    Prev
    Next
    INDEX
    Explanations

    programming variable and code indicators

    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
    𝒋
    0.84
    Р
    0.84
    ी
    0.82
     autre
    0.81
    ㄼ
    0.78
     odkazy
    0.77
     बीटल
    0.76
    অর্থাৎ
    0.76
     foe
    0.76
    б
    0.75
    POSITIVE LOGITS
    t
    0.80
    matic
    0.74
    ទទួលបាន
    0.74
    
    0.74
    ﻪ
    0.73
    তা
    0.72
     newly
    0.69
    യും
    0.69
     принад
    0.67
    ாவின்
    0.67
    Activations Density 0.041%

    No Known Activations