© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    improvements and explanations

    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
    Caution
    0.79
     T
    0.76
     Caution
    0.76
    하
    0.75
     Neighbor
    0.74
     W
    0.73
     Trivia
    0.71
     Snack
    0.71
     Chill
    0.71
     감
    0.71
    POSITIVE LOGITS
    全新的
    1.17
    novation
    1.13
    improved
    1.10
     improved
    1.08
     improvements
    1.05
    jelasan
    1.05
    ifferentiated
    1.04
     optimised
    1.04
     verbess
    1.04
     متعدد
    1.04
    Activations Density 0.421%

    No Known Activations