© 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. 256843
    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
    那我們
    0.50
    iyar
    0.49
     論
    0.47
    がる
    0.46
    દાર
    0.46
     Badminton
    0.46
    如果我们
    0.45
    akyat
    0.44
     ὁ
    0.43
     selfishness
    0.43
    POSITIVE LOGITS
    oury
    0.45
     bacter
    0.44
    bacteria
    0.43
     entfernen
    0.43
     bacteria
    0.43
     bactéri
    0.42
    ंट
    0.41
     fluoride
    0.40
     मेथ
    0.39
     fertiliser
    0.39
    Activations Density 0.000%

    No Known Activations