© 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. 255973
    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
    disamb
    0.50
    arod
    0.48
    AF
    0.47
    ar
    0.47
    今年も
    0.47
    N
    0.47
     nen
    0.47
    arad
    0.46
    adjoint
    0.46
    มัน
    0.46
    POSITIVE LOGITS
     ముందుకు
    0.47
    利的
    0.45
    твер
    0.44
     చూ
    0.44
    кола
    0.44
    樾
    0.44
    كو
    0.42
    态度
    0.42
    昷
    0.42
    šení
    0.41
    Activations Density 0.000%

    No Known Activations