© 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. 254297
    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
    ل
    0.53
    ন
    0.52
     выбра
    0.48
    ه
    0.46
     erreur
    0.46
    ধরনের
    0.46
    ateur
    0.46
    繋がりたい
    0.45
     مە
    0.45
    দি
    0.44
    POSITIVE LOGITS
    techniques
    0.43
     techniques
    0.42
     técnicas
    0.41
     localObject
    0.41
    嘤
    0.41
    斂
    0.41
    sales
    0.40
    am
    0.40
    ॅन
    0.39
    Bytes
    0.39
    Activations Density 0.000%

    No Known Activations