© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8933
    Prev
    Next
    INDEX
    Explanations

    what those such

    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_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
     была
    0.45
    <unused254>
    0.45
     gerçekleş
    0.44
     सिलसिले
    0.43
    ალაქ
    0.42
    <unused501>
    0.42
    мма
    0.42
     konuda
    0.42
    <unused277>
    0.42
     happens
    0.42
    POSITIVE LOGITS
     (
    0.58
    ↵
    0.54
     With
    0.44
    0.44
     with
    0.43
    /
    0.42
     If
    0.38
     ​​
    0.38
      
    0.37
    （
    0.36
    Activations Density 0.087%

    No Known Activations