© 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. 260578
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,
    0.54
     spatial
    0.48
     genomes
    0.48
     ai
    0.48
     ag
    0.47
     coats
    0.46
     ST
    0.46
     additive
    0.46
     innate
    0.46
     platforms
    0.46
    POSITIVE LOGITS
     כי
    0.65
    ۷
    0.60
     ஆரோ
    0.52
     वॉलेट
    0.52
     చెర్రీ
    0.52
    targetReference
    0.51
    ﾐ
    0.50
     ولي
    0.49
     பகுதி
    0.49
     ደቂ
    0.49
    Activations Density 0.000%

    No Known Activations