© 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. 1816
    Prev
    Next
    INDEX
    Explanations

    PHP use statements

    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
    ssä
    0.91
    regar
    0.87
    ™
    0.85
     ಹಾಗ
    0.82
    effici
    0.81
    retrieve
    0.79
    que
    0.79
    trainer
    0.78
    ണ്ട്
    0.78
    ୁ
    0.78
    POSITIVE LOGITS
     Illuminate
    1.00
     stoked
    0.88
     Invalid
    0.80
     wary
    0.75
     latter
    0.75
     Darius
    0.74
     Kut
    0.74
     Yaj
    0.72
     fungsi
    0.72
    ᓪ
    0.71
    Activations Density 0.003%

    No Known Activations