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. 7229
    Prev
    Next
    INDEX
    Explanations

    brushed his velvet nose

    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
    sto
    2.13
    কারী
    1.91
    st
    1.91
     whereabouts
    1.89
    म
    1.87
    ⺆
    1.85
    তায়
    1.81
     Verdict
    1.78
    aré
    1.78
    Notwithstanding
    1.74
    POSITIVE LOGITS
     nema
    1.84
     Gradually
    1.83
     człowieka
    1.80
    াণ
    1.78
    ^{*}
    1.77
     času
    1.76
     gesamte
    1.68
     هو
    1.68
    在這個
    1.68
     samego
    1.67
    Activations Density 0.000%

    No Known Activations