© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43994
    Prev
    Next
    INDEX
    Explanations

    code and names

    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_31_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
     所以
    0.43
     ну
    0.39
    ↵↵
    0.39
     никак
    0.39
    ed
    0.38
    Examples
    0.38
     암
    0.38
     माफ
    0.38
      
    0.37
     ότι
    0.37
    POSITIVE LOGITS
    డాది
    0.51
    üler
    0.48
     montaña
    0.47
     hareket
    0.46
    wallepics
    0.45
     alquiler
    0.45
     mladi
    0.45
     priprav
    0.45
     الحركه
    0.44
     سوریه
    0.43
    Activations Density 0.001%

    No Known Activations