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. 22-GEMMASCOPE-2-RES-16K
    4. 3787
    Prev
    Next
    INDEX
    Explanations

    links to subsequent technical 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_16k_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
    ۀ
    0.88
     אשר
    0.87
    ӣ
    0.84
    臺灣
    0.83
     сведения
    0.83
    മ്ബ
    0.82
     ವಿಧಾನಸಭಾ
    0.81
     शुभार
    0.81
     बिज़
    0.78
    〈
    0.78
    POSITIVE LOGITS
     ebenfalls
    1.11
     SOME
    0.83
     either
    0.78
     both
    0.71
    上述
    0.70
     samme
    0.69
     comprado
    0.66
     aforementioned
    0.66
     rans
    0.66
     some
    0.65
    Activations Density 0.949%

    No Known Activations