© 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. 257783
    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
    वारीत
    0.50
    Ꮿ
    0.50
     반려
    0.49
     kucing
    0.49
     Infantry
    0.49
     ਤੁ
    0.49
    ഡ്
    0.48
    }$.
    0.48
    Ꮕ
    0.47
    ങ്
    0.47
    POSITIVE LOGITS
    ;
    0.43
    ↵
    0.42
    //
    0.41
    setMessage
    0.41
    пля
    0.40
     появи
    0.38
     BMI
    0.38
    >("
    0.38
    клу
    0.37
    কর
    0.36
    Activations Density 0.001%

    No Known Activations