© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 103789
    Prev
    Next
    INDEX
    Explanations

    doubling time or volume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    などが
    0.52
    ك
    0.50
    라면
    0.50
    RIGHT
    0.49
     manqu
    0.49
     componenti
    0.48
    ਸ
    0.47
     втори
    0.47
    একটি
    0.47
     фина
    0.47
    POSITIVE LOGITS
     Air
    0.55
     Công
    0.55
    θε
    0.54
     爱
    0.53
     by
    0.52
    望
    0.52
     Sailing
    0.52
     ร่วม
    0.51
     Trust
    0.50
     我们
    0.50
    Activations Density 0.000%

    No Known Activations