© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 7
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds

    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_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
     crawling
    1.17
     erst
    1.09
    숲
    1.06
     sicurezza
    1.06
     ques
    1.03
    Quando
    1.03
    étude
    1.00
    로
    1.00
     crawl
    1.00
     clasific
    0.98
    POSITIVE LOGITS
    ocarbon
    1.15
     ringan
    1.05
    िकेशन
    1.05
    ب
    1.00
     sulphide
    0.99
    مة
    0.97
     sulfide
    0.96
    כו
    0.96
     कार्बो
    0.95
     Tempat
    0.94
    Activations Density 0.507%

    No Known Activations