© 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. 257461
    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
    ifikat
    0.43
     Kapitel
    0.43
     etiquetas
    0.42
     ____
    0.40
    👥
    0.40
     طلعت
    0.40
    CreateParams
    0.40
     Anzeigen
    0.39
     Crib
    0.38
    COUR
    0.38
    POSITIVE LOGITS
     resemblance
    0.37
     grot
    0.37
     confidentialité
    0.36
     kama
    0.34
    ြ
    0.34
     lira
    0.33
     chancellor
    0.33
    導
    0.33
    ꞌ
    0.33
     orch
    0.33
    Activations Density 0.018%

    No Known Activations