© 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. 159243
    Prev
    Next
    INDEX
    Explanations

    law or specific terms

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

    immediately before

    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
     millions
    0.49
    リュ
    0.46
    덟
    0.44
     vệ
    0.43
     voiture
    0.43
    얹
    0.43
     اکس
    0.42
     ouvir
    0.41
     rửa
    0.41
    즐
    0.41
    POSITIVE LOGITS
    linearity
    0.51
     CCOC
    0.50
    recht
    0.48
    ீர்க
    0.48
    teres
    0.47
    隼
    0.47
    commission
    0.46
    rätt
    0.46
    䒨
    0.46
     CCN
    0.46
    Activations Density 0.001%

    No Known Activations