© 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. 259009
    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
     платфор
    0.49
     галакти
    0.46
     συμπ
    0.46
     актива
    0.46
    曝光
    0.46
    ቻ
    0.45
     Activ
    0.45
    摀
    0.45
     Activision
    0.44
    反对
    0.44
    POSITIVE LOGITS
     customs
    0.45
    ष्टा
    0.42
     siglo
    0.40
     distinguish
    0.40
    hene
    0.39
     देणे
    0.39
     kör
    0.38
    さは
    0.38
     شود
    0.38
    Birth
    0.38
    Activations Density 0.002%

    No Known Activations