© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    economics and finance terms

    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
    सिक
    0.85
    يها
    0.84
    i
    0.83
    বর্তী
    0.78
    涘
    0.78
    ać
    0.77
    掛
    0.77
    ەت
    0.76
     cort
    0.76
    ių
    0.76
    POSITIVE LOGITS
     βά
    1.04
     codeword
    0.99
    untary
    0.94
     áo
    0.92
     spoken
    0.91
    uerte
    0.90
     stá
    0.90
     coordinadora
    0.90
    𝐸
    0.90
     Sadly
    0.90
    Activations Density 0.001%

    No Known Activations