© 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. 260387
    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
     disclosing
    0.42
     allegedly
    0.42
    ichael
    0.41
     LENGTH
    0.40
    =")
    0.40
    falcon
    0.39
     forgets
    0.38
     dissolves
    0.38
     signify
    0.38
    িবে
    0.38
    POSITIVE LOGITS
    лася
    0.58
    的這個
    0.52
     coleg
    0.50
    Zona
    0.50
    歲
    0.50
    Timer
    0.48
    vykor
    0.48
    的日子
    0.46
     vó
    0.46
    㧋
    0.46
    Activations Density 0.000%

    No Known Activations