© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 206026
    Prev
    Next
    INDEX
    Explanations

    Catherine Pugh

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

    formatting characters

    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
     Magdal
    0.43
    ForResult
    0.41
    گاه
    0.38
     ache
    0.38
     Nevis
    0.38
    寯
    0.38
    نیٹ
    0.37
     Kenyans
    0.37
     identifiable
    0.37
    AKES
    0.37
    POSITIVE LOGITS
    ↵↵↵
    0.80
    ↵↵↵↵
    0.62
    el
    0.58
    ↵↵↵↵↵
    0.55
    ↵↵↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵
    0.49
    elä
    0.48
    bil
    0.48
    zelfde
    0.48
    ↵↵↵↵↵↵↵↵↵
    0.46
    Activations Density 0.004%

    No Known Activations