© 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. 584
    Prev
    Next
    INDEX
    Explanations

    Broadcasting Cognitive spectrum Memory

    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
     treacherous
    0.59
     oppressive
    0.53
     celestial
    0.52
     necklace
    0.51
     true
    0.51
     gemstones
    0.50
    ㅣ
    0.50
     concave
    0.48
     reduce
    0.48
     denominations
    0.48
    POSITIVE LOGITS
     שא
    0.62
     livraison
    0.60
     Utilizing
    0.59
     hỗ
    0.57
    型
    0.56
     Teknologi
    0.56
    າມາດ
    0.55
     летом
    0.54
     Technology
    0.54
     الزمن
    0.54
    Activations Density 1.007%

    No Known Activations