© 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. 120064
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

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

    language model coding

    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
    名は
    0.40
     मार्च
    0.40
     августа
    0.39
     Districts
    0.39
     सुनीता
    0.38
     উন্ন
    0.38
     అన్న
    0.38
    蒴
    0.38
     deportiva
    0.37
     जुलाई
    0.37
    POSITIVE LOGITS
    AFS
    0.59
     TFS
    0.53
    FS
    0.52
     PFS
    0.48
     IFS
    0.46
     FS
    0.46
     FCS
    0.44
    TMS
    0.43
     TMS
    0.43
    OCS
    0.43
    Activations Density 0.036%

    No Known Activations