© 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. 17-GEMMASCOPE-2-RES-16K
    7. 14804
    Prev
    Next
    INDEX
    Explanations

    de-escalating, de-identifying, encrypting, deprotecting

    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
    elves
    1.24
     étrangers
    1.05
     Surrogate
    1.04
    ʂ
    1.03
    boats
    1.03
     گار
    1.02
    ofs
    1.01
     yeasts
    0.98
    ostatic
    0.96
     pectoral
    0.96
    POSITIVE LOGITS
    िंग
    1.45
    करण
    1.42
    ed
    1.41
    ing
    1.35
    化
    1.30
    ating
    1.29
    ization
    1.26
    টিয়ে
    1.26
    ر
    1.25
    騒
    1.24
    Activations Density 0.128%

    No Known Activations