© 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. 126702
    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
     proguardFiles
    0.57
     ditth
    0.55
    s
    0.54
     terzo
    0.52
     języ
    0.52
     plików
    0.52
     تغيير
    0.51
     splike
    0.50
     ワイド
    0.50
     snelheid
    0.50
    POSITIVE LOGITS
     well
    0.55
    良好
    0.53
    잘
    0.53
     खासा
    0.52
    well
    0.52
     adequ
    0.51
     versed
    0.51
    よく
    0.50
     достаточно
    0.50
    는
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.