© 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. 243903
    Prev
    Next
    INDEX
    Explanations

    grouping terms

    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
    фон
    0.55
     دوباره
    0.54
    ہ
    0.53
    Архі
    0.52
     orgull
    0.50
    هرة
    0.47
     célé
    0.47
    جع
    0.46
    کہ
    0.46
    غيرة
    0.46
    POSITIVE LOGITS
     "
    0.63
     clusters
    0.60
        
    0.59
     in
    0.58
    ",
    0.58
     Clusters
    0.55
     /$
    0.54
    :"
    0.53
     Gul
    0.53
         
    0.52
    Activations Density 0.000%

    No Known Activations