© 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. 174514
    Prev
    Next
    INDEX
    Explanations

    friends, family, group, charity

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

    nuanced understanding

    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
    面积
    0.51
     Mountains
    0.50
     Masonic
    0.49
     Beach
    0.49
     Bigg
    0.49
    一致
    0.47
    搧
    0.47
     County
    0.45
     Northeastern
    0.45
     warrantless
    0.45
    POSITIVE LOGITS
                    
    0.52
    탐
    0.50
    Faz
    0.49
     synapses
    0.46
     supersede
    0.44
    spiele
    0.44
     ensinar
    0.44
     eradicate
    0.43
     simulate
    0.43
    putes
    0.43
    Activations Density 0.001%

    No Known Activations