© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15327
    Prev
    Next
    INDEX
    Explanations

    on a scale

    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_17_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
     behalf
    1.62
    िक्रमा
    1.30
    ൂര്‍
    1.02
     three
    0.96
     piracy
    0.94
     occasion
    0.92
    ^{*}+
    0.92
     pedestal
    0.91
     flammable
    0.91
    ൪
    0.91
    POSITIVE LOGITS
    에
    0.95
    ভেদ
    0.89
     निर्धारक
    0.89
    y
    0.88
    ແລະ
    0.85
     prenda
    0.84
    ی
    0.83
     جواب
    0.80
     tanta
    0.80
    yczne
    0.80
    Activations Density 0.023%

    No Known Activations