© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84607
    Prev
    Next
    INDEX
    Explanations

    sustained reductions

    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_40_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
    での
    0.45
     চলবে
    0.45
     when
    0.43
     then
    0.42
     to
    0.41
     因
    0.40
     ensues
    0.40
    )));
    0.38
     lors
    0.38
     during
    0.38
    POSITIVE LOGITS
     nowadays
    0.65
     oftentimes
    0.59
    ということは
    0.54
     ngayon
    0.54
    可以说是
    0.54
     그러니까
    0.53
     ganske
    0.52
     constantemente
    0.52
     довольно
    0.52
     manchmal
    0.50
    Activations Density 0.000%

    No Known Activations