© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 287
    Prev
    Next
    INDEX
    Explanations

    medical, law, charitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    కర
    0.80
     किलोमीटर
    0.78
     been
    0.76
     brochure
    0.76
     BEEN
    0.75
    雎
    0.74
    貞
    0.74
    揀
    0.74
    bé
    0.74
     책임
    0.74
    POSITIVE LOGITS
    呋
    0.55
     Ley
    0.54
    neum
    0.49
     Demp
    0.49
    field
    0.48
     Wied
    0.47
    таю
    0.47
     Law
    0.45
     Medical
    0.45
     Charitable
    0.44
    Activations Density 0.230%

    No Known Activations