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. 17-GEMMASCOPE-2-RES-65K
    4. 46831
    Prev
    Next
    INDEX
    Explanations

    geographic areas and communities

    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_65k_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
    翠
    1.06
    ivist
    1.02
    oteca
    1.01
    ঞ্চল্য
    1.00
    urun
    0.99
     იმ
    0.98
     electrocardi
    0.97
     đựng
    0.97
    পট
    0.96
     Dla
    0.95
    POSITIVE LOGITS
    ्ड
    0.94
     sufferings
    0.90
    卩
    0.90
     squeezed
    0.86
     말미암아
    0.84
     probl
    0.83
     susp
    0.82
     excessive
    0.82
     shortcomings
    0.81
    𝓇
    0.80
    Activations Density 0.016%

    No Known Activations