© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8542
    Prev
    Next
    INDEX
    Explanations

    of + noun phrases

    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
    เรา
    1.90
    ح
    1.76
    情况
    1.70
    問題
    1.68
    У
    1.63
    .(
    1.63
    ১
    1.63
    ї
    1.63
     aquilo
    1.62
    ש
    1.62
    POSITIVE LOGITS
    iary
    1.87
    𝓵
    1.72
     sorts
    1.66
    isjon
    1.57
    م
    1.55
    𝓶
    1.54
    ené
    1.53
    is
    1.51
     sobra
    1.48
    𝓭
    1.47
    Activations Density 0.446%

    No Known Activations