© 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. 6578
    Prev
    Next
    INDEX
    Explanations

    Pakistan and Lahore

    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
    슴
    0.53
     romanzo
    0.46
    iguë
    0.44
    र्दशी
    0.44
    瑉
    0.43
     arbre
    0.42
    Bechyné
    0.41
    akata
    0.40
     पौधा
    0.40
    ölf
    0.40
    POSITIVE LOGITS
     v
    0.43
    в
    0.39
              
    0.39
     Math
    0.39
                
    0.37
                    
    0.37
     August
    0.36
     VI
    0.36
     (
    0.36
     Pack
    0.35
    Activations Density 0.000%

    No Known Activations