© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 117589
    Prev
    Next
    INDEX
    Explanations

    products and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite

    composition or inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝘞
    0.65
    च्युअल
    0.57
    ታዊ
    0.56
    тного
    0.55
    𝘏
    0.55
    ца
    0.54
     ورلڈ
    0.53
     चीज
    0.52
     छु
    0.52
    IsTrue
    0.52
    POSITIVE LOGITS
    就在
    0.48
     Spring
    0.47
    接收
    0.42
    EC
    0.42
     Fas
    0.42
     esistono
    0.42
     dopo
    0.41
    ↵↵↵
    0.41
      
    0.40
     start
    0.40
    Activations Density 0.000%

    No Known Activations