© 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. 258002
    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
    ن
    0.55
    أ
    0.54
     Học
    0.52
     Conrad
    0.51
     Pric
    0.51
     Coon
    0.50
     Pressed
    0.49
    :]
    0.49
    ádiz
    0.49
    ج
    0.49
    POSITIVE LOGITS
     unattainable
    0.54
    trop
    0.51
    ுற
    0.48
    TP
    0.47
    FAT
    0.47
    Belgium
    0.46
     unmet
    0.46
     discontent
    0.46
    anlagen
    0.45
    DMF
    0.44
    Activations Density 0.001%

    No Known Activations